OreX/forge-build
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Bacruru Sakaguchi
2025-10-21 23:06:12 +07:00
commit 384a42b08e
1550 changed files with 2675522 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
backend/README.md Executable file
View File

@@ -0,0 +1 @@
# WIP Backend for Forge

67
backend/args.py Executable file
View File

@@ -0,0 +1,67 @@
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--gpu-device-id", type=int, default=None, metavar="DEVICE_ID")
fp_group = parser.add_mutually_exclusive_group()
fp_group.add_argument("--all-in-fp32", action="store_true")
fp_group.add_argument("--all-in-fp16", action="store_true")
fpunet_group = parser.add_mutually_exclusive_group()
fpunet_group.add_argument("--unet-in-bf16", action="store_true")
fpunet_group.add_argument("--unet-in-fp16", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e4m3fn", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e5m2", action="store_true")
fpvae_group = parser.add_mutually_exclusive_group()
fpvae_group.add_argument("--vae-in-fp16", action="store_true")
fpvae_group.add_argument("--vae-in-fp32", action="store_true")
fpvae_group.add_argument("--vae-in-bf16", action="store_true")
parser.add_argument("--vae-in-cpu", action="store_true")
fpte_group = parser.add_mutually_exclusive_group()
fpte_group.add_argument("--clip-in-fp8-e4m3fn", action="store_true")
fpte_group.add_argument("--clip-in-fp8-e5m2", action="store_true")
fpte_group.add_argument("--clip-in-fp16", action="store_true")
fpte_group.add_argument("--clip-in-fp32", action="store_true")
attn_group = parser.add_mutually_exclusive_group()
attn_group.add_argument("--attention-split", action="store_true")
attn_group.add_argument("--attention-quad", action="store_true")
attn_group.add_argument("--attention-pytorch", action="store_true")
upcast = parser.add_mutually_exclusive_group()
upcast.add_argument("--force-upcast-attention", action="store_true")
upcast.add_argument("--disable-attention-upcast", action="store_true")
parser.add_argument("--disable-xformers", action="store_true")
parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1)
parser.add_argument("--disable-ipex-hijack", action="store_true")
vram_group = parser.add_mutually_exclusive_group()
vram_group.add_argument("--always-gpu", action="store_true")
vram_group.add_argument("--always-high-vram", action="store_true")
vram_group.add_argument("--always-normal-vram", action="store_true")
vram_group.add_argument("--always-low-vram", action="store_true")
vram_group.add_argument("--always-no-vram", action="store_true")
vram_group.add_argument("--always-cpu", action="store_true")
parser.add_argument("--always-offload-from-vram", action="store_true")
parser.add_argument("--pytorch-deterministic", action="store_true")
parser.add_argument("--cuda-malloc", action="store_true")
parser.add_argument("--cuda-stream", action="store_true")
parser.add_argument("--pin-shared-memory", action="store_true")
parser.add_argument("--disable-gpu-warning", action="store_true")
args = parser.parse_known_args()[0]
# Some dynamic args that may be changed by webui rather than cmd flags.
dynamic_args = dict(
embedding_dir='./embeddings',
emphasis_name='original'
)

501
backend/attention.py Executable file
View File

@@ -0,0 +1,501 @@
import math
import torch
import einops
from backend.args import args
from backend import memory_management
from backend.misc.sub_quadratic_attention import efficient_dot_product_attention
BROKEN_XFORMERS = False
if memory_management.xformers_enabled():
import xformers
import xformers.ops
try:
x_vers = xformers.__version__
BROKEN_XFORMERS = x_vers.startswith("0.0.2") and not x_vers.startswith("0.0.20")
except:
pass
FORCE_UPCAST_ATTENTION_DTYPE = memory_management.force_upcast_attention_dtype()
def get_attn_precision(attn_precision=torch.float32):
if args.disable_attention_upcast:
return None
if FORCE_UPCAST_ATTENTION_DTYPE is not None:
return FORCE_UPCAST_ATTENTION_DTYPE
return attn_precision
def exists(val):
return val is not None
def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
if attn_precision == torch.float32:
sim = torch.einsum('b i d, b j d -> b i j', q.float(), k.float()) * scale
else:
sim = torch.einsum('b i d, b j d -> b i j', q, k) * scale
del q, k
if exists(mask):
if mask.dtype == torch.bool:
mask = einops.rearrange(mask, 'b ... -> b (...)')
max_neg_value = -torch.finfo(sim.dtype).max
mask = einops.repeat(mask, 'b j -> (b h) () j', h=h)
sim.masked_fill_(~mask, max_neg_value)
else:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
sim.add_(mask)
sim = sim.softmax(dim=-1)
out = torch.einsum('b i j, b j d -> b i d', sim.to(v.dtype), v)
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return out
def attention_sub_quad(query, key, value, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = query.shape
else:
b, _, dim_head = query.shape
dim_head //= heads
scale = dim_head ** -0.5
if skip_reshape:
query = query.reshape(b * heads, -1, dim_head)
value = value.reshape(b * heads, -1, dim_head)
key = key.reshape(b * heads, -1, dim_head).movedim(1, 2)
else:
query = query.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
value = value.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
key = key.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1)
dtype = query.dtype
upcast_attention = attn_precision == torch.float32 and query.dtype != torch.float32
if upcast_attention:
bytes_per_token = torch.finfo(torch.float32).bits // 8
else:
bytes_per_token = torch.finfo(query.dtype).bits // 8
batch_x_heads, q_tokens, _ = query.shape
_, _, k_tokens = key.shape
qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens
mem_free_total, mem_free_torch = memory_management.get_free_memory(query.device, True)
kv_chunk_size_min = None
kv_chunk_size = None
query_chunk_size = None
for x in [4096, 2048, 1024, 512, 256]:
count = mem_free_total / (batch_x_heads * bytes_per_token * x * 4.0)
if count >= k_tokens:
kv_chunk_size = k_tokens
query_chunk_size = x
break
if query_chunk_size is None:
query_chunk_size = 512
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
hidden_states = efficient_dot_product_attention(
query,
key,
value,
query_chunk_size=query_chunk_size,
kv_chunk_size=kv_chunk_size,
kv_chunk_size_min=kv_chunk_size_min,
use_checkpoint=False,
upcast_attention=upcast_attention,
mask=mask,
)
hidden_states = hidden_states.to(dtype)
hidden_states = hidden_states.unflatten(0, (-1, heads)).transpose(1, 2).flatten(start_dim=2)
return hidden_states
def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
mem_free_total = memory_management.get_free_memory(q.device)
if attn_precision == torch.float32:
element_size = 4
upcast = True
else:
element_size = q.element_size()
upcast = False
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * element_size
modifier = 3
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
# print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB "
# f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}")
if steps > 64:
max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64
raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
# print("steps", steps, mem_required, mem_free_total, modifier, q.element_size(), tensor_size)
first_op_done = False
cleared_cache = False
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
if upcast:
with torch.autocast(enabled=False, device_type='cuda'):
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end].float(), k.float()) * scale
else:
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end], k) * scale
if mask is not None:
if len(mask.shape) == 2:
s1 += mask[i:end]
else:
s1 += mask[:, i:end]
s2 = s1.softmax(dim=-1).to(v.dtype)
del s1
first_op_done = True
r1[:, i:end] = torch.einsum('b i j, b j d -> b i d', s2, v)
del s2
break
except memory_management.OOM_EXCEPTION as e:
if first_op_done == False:
memory_management.soft_empty_cache(True)
if cleared_cache == False:
cleared_cache = True
print("out of memory error, emptying cache and trying again")
continue
steps *= 2
if steps > 64:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
else:
raise e
del q, k, v
r1 = (
r1.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return r1
def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
if BROKEN_XFORMERS and b * heads > 65535:
return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape)
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.reshape(b, -1, heads, dim_head),
(q, k, v),
)
if mask is not None:
pad = 8 - q.shape[1] % 8
mask_out = torch.empty([q.shape[0], q.shape[1], q.shape[1] + pad], dtype=q.dtype, device=q.device)
mask_out[:, :, :mask.shape[-1]] = mask
mask = mask_out[:, :, :mask.shape[-1]]
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask)
if skip_reshape:
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
else:
out = (
out.reshape(b, -1, heads * dim_head)
)
return out
def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
q, k, v = map(
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
(q, k, v),
)
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
out = (
out.transpose(1, 2).reshape(b, -1, heads * dim_head)
)
return out
def slice_attention_single_head_spatial(q, k, v):
r1 = torch.zeros_like(k, device=q.device)
scale = (int(q.shape[-1]) ** (-0.5))
mem_free_total = memory_management.get_free_memory(q.device)
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[2] * q.element_size()
modifier = 3 if q.element_size() == 2 else 2.5
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
s1 = torch.bmm(q[:, i:end], k) * scale
s2 = torch.nn.functional.softmax(s1, dim=2).permute(0, 2, 1)
del s1
r1[:, :, i:end] = torch.bmm(v, s2)
del s2
break
except memory_management.OOM_EXCEPTION as e:
memory_management.soft_empty_cache(True)
steps *= 2
if steps > 128:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
return r1
def normal_attention_single_head_spatial(q, k, v):
# compute attention
b, c, h, w = q.shape
q = q.reshape(b, c, h * w)
q = q.permute(0, 2, 1) # b,hw,c
k = k.reshape(b, c, h * w) # b,c,hw
v = v.reshape(b, c, h * w)
r1 = slice_attention_single_head_spatial(q, k, v)
h_ = r1.reshape(b, c, h, w)
del r1
return h_
def xformers_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, C, -1).transpose(1, 2).contiguous(),
(q, k, v),
)
try:
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)
out = out.transpose(1, 2).reshape(B, C, H, W)
except NotImplementedError as e:
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
def pytorch_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, 1, C, -1).transpose(2, 3).contiguous(),
(q, k, v),
)
try:
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=False)
out = out.transpose(2, 3).reshape(B, C, H, W)
except memory_management.OOM_EXCEPTION as e:
print("scaled_dot_product_attention OOMed: switched to slice attention")
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
if memory_management.xformers_enabled():
print("Using xformers cross attention")
attention_function = attention_xformers
elif memory_management.pytorch_attention_enabled():
print("Using pytorch cross attention")
attention_function = attention_pytorch
elif args.attention_split:
print("Using split optimization for cross attention")
attention_function = attention_split
else:
print("Using sub quadratic optimization for cross attention")
attention_function = attention_sub_quad
if memory_management.xformers_enabled_vae():
print("Using xformers attention for VAE")
attention_function_single_head_spatial = xformers_attention_single_head_spatial
elif memory_management.pytorch_attention_enabled():
print("Using pytorch attention for VAE")
attention_function_single_head_spatial = pytorch_attention_single_head_spatial
else:
print("Using split attention for VAE")
attention_function_single_head_spatial = normal_attention_single_head_spatial
class AttentionProcessorForge:
def __call__(self, attn, hidden_states, encoder_hidden_states, attention_mask=None, temb=None, *args, **kwargs):
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
hidden_states = attention_function(query, key, value, heads=attn.heads, mask=attention_mask)
hidden_states = attn.to_out[0](hidden_states)
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states

87
backend/diffusion_engine/base.py Executable file
View File

@@ -0,0 +1,87 @@
import torch
import safetensors.torch as sf
from backend import utils
class ForgeObjects:
def __init__(self, unet, clip, vae, clipvision):
self.unet = unet
self.clip = clip
self.vae = vae
self.clipvision = clipvision
def shallow_copy(self):
return ForgeObjects(
self.unet,
self.clip,
self.vae,
self.clipvision
)
class ForgeDiffusionEngine:
matched_guesses = []
def __init__(self, estimated_config, huggingface_components):
self.model_config = estimated_config
self.is_inpaint = estimated_config.inpaint_model()
self.forge_objects = None
self.forge_objects_original = None
self.forge_objects_after_applying_lora = None
self.current_lora_hash = str([])
self.fix_for_webui_backward_compatibility()
def set_clip_skip(self, clip_skip):
pass
def get_first_stage_encoding(self, x):
return x # legacy code, do not change
def get_learned_conditioning(self, prompt: list[str]):
pass
def encode_first_stage(self, x):
pass
def decode_first_stage(self, x):
pass
def get_prompt_lengths_on_ui(self, prompt):
return 0, 75
def is_webui_legacy_model(self):
return self.is_sd1 or self.is_sd2 or self.is_sdxl or self.is_sd3
def fix_for_webui_backward_compatibility(self):
self.tiling_enabled = False
self.first_stage_model = None
self.cond_stage_model = None
self.use_distilled_cfg_scale = False
self.is_sd1 = False
self.is_sd2 = False
self.is_sdxl = False
self.is_sd3 = False
return
def save_unet(self, filename):
sd = utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model)
sf.save_file(sd, filename)
return filename
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='text_encoders.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='vae.')
)
sf.save_file(sd, filename)
return filename

114
backend/diffusion_engine/flux.py Executable file
View File

@@ -0,0 +1,114 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend.modules.k_prediction import PredictionFlux
from backend import memory_management
class Flux(ForgeDiffusionEngine):
matched_guesses = [model_list.Flux, model_list.FluxSchnell]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
't5xxl': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
't5xxl': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
if 'schnell' in estimated_config.huggingface_repo.lower():
k_predictor = PredictionFlux(
mu=1.0
)
else:
k_predictor = PredictionFlux(
seq_len=4096,
base_seq_len=256,
max_seq_len=4096,
base_shift=0.5,
max_shift=1.15,
)
self.use_distilled_cfg_scale = True
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler=None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=True,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_l, pooled_l = self.text_processing_engine_l(prompt)
cond_t5 = self.text_processing_engine_t5(prompt)
cond = dict(crossattn=cond_t5, vector=pooled_l)
if self.use_distilled_cfg_scale:
distilled_cfg_scale = getattr(prompt, 'distilled_cfg_scale', 3.5) or 3.5
cond['guidance'] = torch.FloatTensor([distilled_cfg_scale] * len(prompt))
print(f'Distilled CFG Scale: {distilled_cfg_scale}')
else:
print('Distilled CFG Scale will be ignored for Schnell')
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)

100
backend/diffusion_engine/sd15.py Executable file
View File

@@ -0,0 +1,100 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion(ForgeDiffusionEngine):
matched_guesses = [model_list.SD15]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd1 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD15.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

100
backend/diffusion_engine/sd20.py Executable file
View File

@@ -0,0 +1,100 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion2(ForgeDiffusionEngine):
matched_guesses = [model_list.SD20]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_h': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_h': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_h,
tokenizer=clip.tokenizer.clip_h,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_h',
embedding_expected_shape=1024,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd2 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD20.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

149
backend/diffusion_engine/sd35.py Executable file
View File

@@ -0,0 +1,149 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.modules.k_prediction import PredictionDiscreteFlow
from modules.shared import opts
## patch SD3 Class in huggingface_guess.model_list
def SD3_clip_target(self, state_dict={}):
return {'clip_l': 'text_encoder', 'clip_g': 'text_encoder_2', 't5xxl': 'text_encoder_3'}
model_list.SD3.unet_target = 'transformer'
model_list.SD3.clip_target = SD3_clip_target
## end patch
class StableDiffusion3(ForgeDiffusionEngine):
matched_guesses = [model_list.SD3]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2'],
't5xxl' : huggingface_components['text_encoder_3']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2'],
't5xxl' : huggingface_components['tokenizer_3']
}
)
k_predictor = PredictionDiscreteFlow(shift=3.0)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler= None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=1280,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd3 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_g, g_pooled = self.text_processing_engine_g(prompt)
cond_l, l_pooled = self.text_processing_engine_l(prompt)
if opts.sd3_enable_t5:
cond_t5 = self.text_processing_engine_t5(prompt)
else:
cond_t5 = torch.zeros([len(prompt), 256, 4096]).to(cond_l.device)
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
l_pooled = torch.zeros_like(l_pooled)
g_pooled = torch.zeros_like(g_pooled)
cond_l = torch.zeros_like(cond_l)
cond_g = torch.zeros_like(cond_g)
cond_t5 = torch.zeros_like(cond_t5)
cond_lg = torch.cat([cond_l, cond_g], dim=-1)
cond_lg = torch.nn.functional.pad(cond_lg, (0, 4096 - cond_lg.shape[-1]))
cond = dict(
crossattn=torch.cat([cond_lg, cond_t5], dim=-2),
vector=torch.cat([l_pooled, g_pooled], dim=-1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)

272
backend/diffusion_engine/sdxl.py Executable file
View File

@@ -0,0 +1,272 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.nn.unet import Timestep
import safetensors.torch as sf
from backend import utils
from modules.shared import opts
class StableDiffusionXL(ForgeDiffusionEngine):
matched_guesses = [model_list.SDXL]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=False,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=True,
final_layer_norm=False,
)
self.embedder = Timestep(256)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sdxl = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_l = self.text_processing_engine_l(prompt)
cond_g, clip_pooled = self.text_processing_engine_g(prompt)
width = getattr(prompt, 'width', 1024) or 1024
height = getattr(prompt, 'height', 1024) or 1024
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
crop_w = opts.sdxl_crop_left
crop_h = opts.sdxl_crop_top
target_width = width
target_height = height
out = [
self.embedder(torch.Tensor([height])), self.embedder(torch.Tensor([width])),
self.embedder(torch.Tensor([crop_h])), self.embedder(torch.Tensor([crop_w])),
self.embedder(torch.Tensor([target_height])), self.embedder(torch.Tensor([target_width]))
]
flat = torch.flatten(torch.cat(out)).unsqueeze(dim=0).repeat(clip_pooled.shape[0], 1).to(clip_pooled)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
clip_pooled = torch.zeros_like(clip_pooled)
cond_l = torch.zeros_like(cond_l)
cond_g = torch.zeros_like(cond_g)
cond = dict(
crossattn=torch.cat([cond_l, cond_g], dim=2),
vector=torch.cat([clip_pooled, flat], dim=1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine_l.process_texts([prompt])
return token_count, self.text_processing_engine_l.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SDXL.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename
class StableDiffusionXLRefiner(ForgeDiffusionEngine):
matched_guesses = [model_list.SDXLRefiner]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_g': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_g': huggingface_components['tokenizer'],
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=True,
final_layer_norm=False,
)
self.embedder = Timestep(256)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sdxl = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_g, clip_pooled = self.text_processing_engine_g(prompt)
width = getattr(prompt, 'width', 1024) or 1024
height = getattr(prompt, 'height', 1024) or 1024
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
crop_w = opts.sdxl_crop_left
crop_h = opts.sdxl_crop_top
aesthetic = opts.sdxl_refiner_low_aesthetic_score if is_negative_prompt else opts.sdxl_refiner_high_aesthetic_score
out = [
self.embedder(torch.Tensor([height])), self.embedder(torch.Tensor([width])),
self.embedder(torch.Tensor([crop_h])), self.embedder(torch.Tensor([crop_w])),
self.embedder(torch.Tensor([aesthetic]))
]
flat = torch.flatten(torch.cat(out)).unsqueeze(dim=0).repeat(clip_pooled.shape[0], 1).to(clip_pooled)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
clip_pooled = torch.zeros_like(clip_pooled)
cond_g = torch.zeros_like(cond_g)
cond = dict(
crossattn=cond_g,
vector=torch.cat([clip_pooled, flat], dim=1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine_g.process_texts([prompt])
return token_count, self.text_processing_engine_g.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SDXLRefiner.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

25
backend/huggingface/Kwai-Kolors/Kolors/model_index.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.18.0.dev0",
"force_zeros_for_empty_prompt": true,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"kolors",
"ChatGLMModel"
],
"tokenizer": [
"kolors",
"ChatGLMTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

22
backend/huggingface/Kwai-Kolors/Kolors/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.18.0.dev0",
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"beta_end": 0.014,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"interpolation_type": "linear",
"num_train_timesteps": 1100,
"prediction_type": "epsilon",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

42
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/config.json Executable file
View File

@@ -0,0 +1,42 @@
{
"_name_or_path": "THUDM/chatglm3-6b-base",
"model_type": "chatglm",
"architectures": [
"ChatGLMModel"
],
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"bias_dropout_fusion": true,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_layers": 28,
"original_rope": true,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"rmsnorm": true,
"seq_length": 32768,
"use_cache": true,
"torch_dtype": "float16",
"transformers_version": "4.30.2",
"tie_word_embeddings": false,
"eos_token_id": 2,
"pad_token_id": 0
}

207
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/pytorch_model.bin.index.json Executable file
View File

@@ -0,0 +1,207 @@
{
"metadata": {
"total_size": 12487168064
},
"weight_map": {
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
}
}

12
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/tokenizer_config.json Executable file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/vocab.txt Executable file
View File

Binary file not shown.

12
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/vocab.txt Executable file
View File

Binary file not shown.

72
backend/huggingface/Kwai-Kolors/Kolors/unet/config.json Executable file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": 4096,
"encoder_hid_dim_type": "text_proj",
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 5632,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

31
backend/huggingface/Kwai-Kolors/Kolors/vae/config.json Executable file
View File

@@ -0,0 +1,31 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.18.0.dev0",
"_name_or_path": "./vae",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

41
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/model_index.json Executable file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "HunyuanDiTPipeline",
"_diffusers_version": "0.29.0.dev0",
"feature_extractor": [
null,
null
],
"requires_safety_checker": true,
"safety_checker": [
null,
null
],
"scheduler": [
"diffusers",
"DDPMScheduler"
],
"text_encoder": [
"transformers",
"BertModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"BertTokenizer"
],
"tokenizer_2": [
"transformers",
"T5Tokenizer"
],
"transformer": [
"diffusers",
"HunyuanDiT2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

21
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,21 @@
{
"_class_name": "DDPMScheduler",
"_diffusers_version": "0.29.0.dev0",
"beta_end": 0.03,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"num_train_timesteps": 1000,
"prediction_type": "v_prediction",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"variance_type": "fixed_small"
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder/config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"directionality": "bidi",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 47020
}

32
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"T5EncoderModel"
],
"classifier_dropout": 0.0,
"d_ff": 5120,
"d_kv": 64,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"use_cache": true,
"vocab_size": 250112
}

226
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 6679834624
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

37
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

57
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,57 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 77,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

47020
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/vocab.txt Executable file
View File

File diff suppressed because it is too large Load Diff

23
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,23 @@
{
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

39
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,39 @@
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

20
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/transformer/config.json Executable file
View File

@@ -0,0 +1,20 @@
{
"_class_name": "HunyuanDiT2DModel",
"_diffusers_version": "0.29.0.dev0",
"activation_fn": "gelu-approximate",
"attention_head_dim": 88,
"cross_attention_dim": 1024,
"cross_attention_dim_t5": 2048,
"hidden_size": 1408,
"in_channels": 4,
"learn_sigma": true,
"mlp_ratio": 4.3637,
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_layers": 40,
"patch_size": 2,
"pooled_projection_dim": 1024,
"sample_size": 128,
"text_len": 77,
"text_len_t5": 256
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/vae/config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.29.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

32
backend/huggingface/black-forest-labs/FLUX.1-dev/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "FluxPipeline",
"_diffusers_version": "0.30.0.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"FluxTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

11
backend/huggingface/black-forest-labs/FLUX.1-dev/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,11 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.30.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"max_image_seq_len": 4096,
"max_shift": 1.15,
"num_train_timesteps": 1000,
"shift": 3.0,
"use_dynamic_shifting": true
}

25
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"vocab_size": 49408
}

22
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "gelu_pytorch_tanh",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}

226
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 9524621312
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

48895
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

125
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,125 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

129428
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer.json Executable file
View File

File diff suppressed because one or more lines are too long

939
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,939 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": false,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

14
backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/config.json Executable file
View File

@@ -0,0 +1,14 @@
{
"_class_name": "FluxTransformer2DModel",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev/transformer",
"attention_head_dim": 128,
"guidance_embeds": true,
"in_channels": 64,
"joint_attention_dim": 4096,
"num_attention_heads": 24,
"num_layers": 19,
"num_single_layers": 38,
"patch_size": 1,
"pooled_projection_dim": 768
}

1167
backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/diffusion_pytorch_model.safetensors.index.json Executable file
View File

File diff suppressed because it is too large Load Diff

38
backend/huggingface/black-forest-labs/FLUX.1-dev/vae/config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

32
backend/huggingface/black-forest-labs/FLUX.1-schnell/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "FluxPipeline",
"_diffusers_version": "0.30.0.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"FluxTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

11
backend/huggingface/black-forest-labs/FLUX.1-schnell/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,11 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.30.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"max_image_seq_len": 4096,
"max_shift": 1.15,
"num_train_timesteps": 1000,
"shift": 1.0,
"use_dynamic_shifting": false
}

25
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"vocab_size": 49408
}

22
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "gelu_pytorch_tanh",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}

226
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 9524621312
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

48895
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

125
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,125 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

129428
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer.json Executable file
View File

File diff suppressed because one or more lines are too long

939
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,939 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": false,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

13
backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/config.json Executable file
View File

@@ -0,0 +1,13 @@
{
"_class_name": "FluxTransformer2DModel",
"_diffusers_version": "0.30.0.dev0",
"attention_head_dim": 128,
"guidance_embeds": false,
"in_channels": 64,
"joint_attention_dim": 4096,
"num_attention_heads": 24,
"num_layers": 19,
"num_single_layers": 38,
"patch_size": 1,
"pooled_projection_dim": 768
}

1163
backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/diffusion_pytorch_model.safetensors.index.json Executable file
View File

File diff suppressed because it is too large Load Diff

38
backend/huggingface/black-forest-labs/FLUX.1-schnell/vae/config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

35
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/model_index.json Executable file
View File

@@ -0,0 +1,35 @@
{
"_class_name": "StableDiffusionXLInpaintPipeline",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
"force_zeros_for_empty_prompt": true,
"requires_aesthetics_score": false,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

18
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,18 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.21.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"interpolation_type": "linear",
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder_2",
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

78
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/unet/config.json Executable file
View File

@@ -0,0 +1,78 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "valhalla/sdxl-inpaint-ema",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"decay": 0.9999,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"inv_gamma": 1.0,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"min_decay": 0.0,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"optimization_step": 37000,
"out_channels": 4,
"power": 0.6666666666666666,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": null,
"update_after_step": 0,
"use_ema_warmup": false,
"use_linear_projection": true
}

32
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/vae/config.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

42
backend/huggingface/lllyasviel/control_v11p_sd15_canny/config.json Executable file
View File

@@ -0,0 +1,42 @@
{
"_class_name": "ControlNetModel",
"_diffusers_version": "0.16.0.dev0",
"_name_or_path": "/home/patrick/controlnet_v1_1/control_v11p_sd15_canny",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"class_embed_type": null,
"conditioning_embedding_out_channels": [
16,
32,
96,
256
],
"controlnet_conditioning_channel_order": "rgb",
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_class_embeds": null,
"only_cross_attention": false,
"projection_class_embeddings_input_dim": null,
"resnet_time_scale_shift": "default",
"upcast_attention": false,
"use_linear_projection": false
}

41
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/model_index.json Executable file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.27.0.dev0",
"feature_extractor": [
null,
null
],
"force_zeros_for_empty_prompt": true,
"image_encoder": [
null,
null
],
"scheduler": [
"diffusers",
"EDMDPMSolverMultistepScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

19
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,19 @@
{
"_class_name": "EDMDPMSolverMultistepScheduler",
"_diffusers_version": "0.27.0.dev0",
"algorithm_type": "dpmsolver++",
"dynamic_thresholding_ratio": 0.995,
"euler_at_final": false,
"final_sigmas_type": "zero",
"lower_order_final": true,
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"rho": 7.0,
"sample_max_value": 1.0,
"sigma_data": 0.5,
"sigma_max": 80.0,
"sigma_min": 0.002,
"solver_order": 2,
"solver_type": "midpoint",
"thresholding": false
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder/config.json Executable file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

38
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "!",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

72
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/unet/config.json Executable file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

43
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/vae/config.json Executable file
View File

@@ -0,0 +1,43 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"latents_mean": [
-1.6574,
1.886,
-1.383,
2.5155
],
"latents_std": [
8.4927,
5.9022,
6.5498,
5.2299
],
"scaling_factor": 0.5
}

36
backend/huggingface/runwayml/stable-diffusion-inpainting/config.json Executable file
View File

@@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0.dev0",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"out_channels": 4,
"sample_size": 64,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
]
}

20
backend/huggingface/runwayml/stable-diffusion-inpainting/feature_extractor/preprocessor_config.json Executable file
View File

@@ -0,0 +1,20 @@
{
"crop_size": 224,
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"size": 224
}

32
backend/huggingface/runwayml/stable-diffusion-inpainting/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "StableDiffusionInpaintPipeline",
"_diffusers_version": "0.6.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"DDIMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

177
backend/huggingface/runwayml/stable-diffusion-inpainting/safety_checker/config.json Executable file
View File

@@ -0,0 +1,177 @@
{
"_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
"architectures": [
"StableDiffusionSafetyChecker"
],
"initializer_factor": 1.0,
"logit_scale_init_value": 2.6592,
"model_type": "clip",
"projection_dim": 768,
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 77,
"min_length": 0,
"model_type": "clip_text_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"prefix": null,
"problem_type": null,
"projection_dim": 512,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 49408
},
"text_config_dict": {
"hidden_size": 768,
"intermediate_size": 3072,
"num_attention_heads": 12,
"num_hidden_layers": 12
},
"torch_dtype": "float32",
"transformers_version": null,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 224,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "clip_vision_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"problem_type": null,
"projection_dim": 512,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false
},
"vision_config_dict": {
"hidden_size": 1024,
"intermediate_size": 4096,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14
}
}

13
backend/huggingface/runwayml/stable-diffusion-inpainting/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,13 @@
{
"_class_name": "DDIMScheduler",
"_diffusers_version": "0.6.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"num_train_timesteps": 1000,
"set_alpha_to_one": false,
"steps_offset": 1,
"trained_betas": null,
"skip_prk_steps": true
}

25
backend/huggingface/runwayml/stable-diffusion-inpainting/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.22.0.dev0",
"vocab_size": 49408
}

48895
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

34
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,34 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"name_or_path": "openai/clip-vit-large-patch14",
"pad_token": "<|endoftext|>",
"special_tokens_map_file": "./special_tokens_map.json",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More