lllyasviel/stable-diffusion-webui-forge
1
0
Fork 0
mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2026-04-25 00:39:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2183 from graemeniedermayer/sd35_integration

Browse Source 
sd3.5 integration (naive)
This commit is contained in:
lllyasviel
2024-10-28 21:54:10 -07:00
committed by GitHub
parent 623778a3a3 1363999fb1
commit 2d5b6cacef
32 changed files with 332140 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

137
backend/diffusion_engine/sd35.py Normal file
View File

@@ -0,0 +1,137 @@
import torch
from huggingface_guess import model_list
# from huggingface_guess.latent import SD3
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
class StableDiffusion3(ForgeDiffusionEngine):
matched_guesses = [model_list.SD35]
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'],
'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 enabled?
cond_t5 = self.text_processing_engine_t5(prompt)
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)

40
backend/huggingface/stabilityai/stable-diffusion-3.5-large/model_index.json Normal file
View File

@@ -0,0 +1,40 @@
{
"_class_name": "StableDiffusion3Pipeline",
"_diffusers_version": "0.30.3.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModelWithProjection"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"text_encoder_3": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_3": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"SD3Transformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

6
backend/huggingface/stabilityai/stable-diffusion-3.5-large/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.29.0.dev0",
"num_train_timesteps": 1000,
"shift": 3.0
}

24
backend/huggingface/stabilityai/stable-diffusion-3.5-large/text_encoder/config.json Normal 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": "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": "4.41.2",
"vocab_size": 49408
}

24
backend/huggingface/stabilityai/stable-diffusion-3.5-large/text_encoder_2/config.json Normal 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": "float16",
"transformers_version": "4.41.2",
"vocab_size": 49408
}

31
backend/huggingface/stabilityai/stable-diffusion-3.5-large/text_encoder_3/config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"architectures": [
"T5EncoderModel"
],
"classifier_dropout": 0.0,
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"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": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32128
}

226
backend/huggingface/stabilityai/stable-diffusion-3.5-large/text_encoder_3/model.safetensors.index.json Normal 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/stabilityai/stable-diffusion-3.5-large/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer/special_tokens_map.json Normal 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/stabilityai/stable-diffusion-3.5-large/tokenizer/tokenizer_config.json Normal 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/stabilityai/stable-diffusion-3.5-large/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_2/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_2/special_tokens_map.json Normal 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": "!",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

38
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_2/tokenizer_config.json Normal 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": 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": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_2/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

125
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_3/special_tokens_map.json Normal 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
}
}

BIN
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_3/spiece.model Normal file
View File

Binary file not shown.

129428
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_3/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

940
backend/huggingface/stabilityai/stable-diffusion-3.5-large/tokenizer_3/tokenizer_config.json Normal file
View File

@@ -0,0 +1,940 @@
{
"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
},
"32000": {
"content": "<extra_id_99>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"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": true,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

16
backend/huggingface/stabilityai/stable-diffusion-3.5-large/transformer/config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"_class_name": "SD3Transformer2DModel",
"_diffusers_version": "0.31.0.dev0",
"attention_head_dim": 64,
"caption_projection_dim": 2432,
"in_channels": 16,
"joint_attention_dim": 4096,
"num_attention_heads": 38,
"num_layers": 38,
"out_channels": 16,
"patch_size": 2,
"pooled_projection_dim": 2048,
"pos_embed_max_size": 192,
"qk_norm": "rms_norm",
"sample_size": 128
}

1234
backend/huggingface/stabilityai/stable-diffusion-3.5-large/transformer/diffusion_pytorch_model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

38
backend/huggingface/stabilityai/stable-diffusion-3.5-large/vae/config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.31.0.dev0",
"_name_or_path": "../sdxl-vae/",
"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": 1.5305,
"shift_factor": 0.0609,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

30
backend/loader.py
View File

@@ -19,11 +19,12 @@ from backend.nn.unet import IntegratedUNet2DConditionModel
from backend.diffusion_engine.sd15 import StableDiffusion
from backend.diffusion_engine.sd20 import StableDiffusion2
from backend.diffusion_engine.sd35 import StableDiffusion3
from backend.diffusion_engine.sdxl import StableDiffusionXL
from backend.diffusion_engine.flux import Flux
possible_models = [StableDiffusion, StableDiffusion2, StableDiffusionXL, Flux]
possible_models = [StableDiffusion, StableDiffusion2, StableDiffusionXL, StableDiffusion3, Flux]
logging.getLogger("diffusers").setLevel(logging.ERROR)
@@ -107,7 +108,7 @@ def load_huggingface_component(guess, component_name, lib_name, cls_name, repo_p
load_state_dict(model, state_dict, log_name=cls_name, ignore_errors=['transformer.encoder.embed_tokens.weight', 'logit_scale'])
return model
if cls_name in ['UNet2DConditionModel', 'FluxTransformer2DModel']:
if cls_name in ['UNet2DConditionModel', 'FluxTransformer2DModel', 'SD3Transformer2DModel']:
assert isinstance(state_dict, dict) and len(state_dict) > 16, 'You do not have model state dict!'
model_loader = None
@@ -116,6 +117,9 @@ def load_huggingface_component(guess, component_name, lib_name, cls_name, repo_p
if cls_name == 'FluxTransformer2DModel':
from backend.nn.flux import IntegratedFluxTransformer2DModel
model_loader = lambda c: IntegratedFluxTransformer2DModel(**c)
if cls_name == 'SD3Transformer2DModel':
from modules.models.sd35.mmditx import MMDiTX
model_loader = lambda c: MMDiTX(**c)
unet_config = guess.unet_config.copy()
state_dict_parameters = memory_management.state_dict_parameters(state_dict)
@@ -170,7 +174,7 @@ def load_huggingface_component(guess, component_name, lib_name, cls_name, repo_p
return None
def replace_state_dict(sd, asd, guess):
def replace_state_dict(sd, asd, guess, is_clip_g = False):
vae_key_prefix = guess.vae_key_prefix[0]
text_encoder_key_prefix = guess.text_encoder_key_prefix[0]
@@ -210,11 +214,18 @@ def replace_state_dict(sd, asd, guess):
sd[vae_key_prefix + k] = v
if 'text_model.encoder.layers.0.layer_norm1.weight' in asd:
keys_to_delete = [k for k in sd if k.startswith(f"{text_encoder_key_prefix}clip_l.")]
for k in keys_to_delete:
del sd[k]
for k, v in asd.items():
sd[f"{text_encoder_key_prefix}clip_l.transformer.{k}"] = v
if is_clip_g:
keys_to_delete = [k for k in sd if k.startswith(f"{text_encoder_key_prefix}clip_g.")]
for k in keys_to_delete:
del sd[k]
for k, v in asd.items():
sd[f"{text_encoder_key_prefix}clip_g.transformer.{k}"] = v
else:
keys_to_delete = [k for k in sd if k.startswith(f"{text_encoder_key_prefix}clip_l.")]
for k in keys_to_delete:
del sd[k]
for k, v in asd.items():
sd[f"{text_encoder_key_prefix}clip_l.transformer.{k}"] = v
if 'encoder.block.0.layer.0.SelfAttention.k.weight' in asd:
keys_to_delete = [k for k in sd if k.startswith(f"{text_encoder_key_prefix}t5xxl.")]
@@ -241,8 +252,9 @@ def split_state_dict(sd, additional_state_dicts: list = None):
if isinstance(additional_state_dicts, list):
for asd in additional_state_dicts:
is_clip_g = 'clip_g' in asd
asd = load_torch_file(asd)
sd = replace_state_dict(sd, asd, guess)
sd = replace_state_dict(sd, asd, guess, is_clip_g)
guess.clip_target = guess.clip_target(sd)
guess.model_type = guess.model_type(sd)

25
backend/modules/k_prediction.py
View File

@@ -251,6 +251,31 @@ class PredictionFlow(AbstractPrediction):
return 1.0 - percent
class PredictionDiscreteFlow(AbstractPrediction):
def __init__(self, sigma_data=1.0, prediction_type='const', shift=1.0, timesteps = 1000):
super().__init__(sigma_data=sigma_data, prediction_type=prediction_type)
self.shift = shift
ts = self.sigma(torch.arange(1, timesteps + 1, 1))
self.register_buffer("sigmas", ts)
@property
def sigma_min(self):
return self.sigmas[0]
@property
def sigma_max(self):
return self.sigmas[-1]
def timestep(self, sigma):
return sigma * 1000
def sigma(self, timestep: torch.Tensor):
timestep = timestep / 1000.0
if self.shift == 1.0:
return timestep
return self.shift * timestep / (1 + (self.shift - 1) * timestep)
class PredictionFlux(AbstractPrediction):
def __init__(self, sigma_data=1.0, prediction_type='const', shift=1.15, timesteps=10000):
super().__init__(sigma_data=sigma_data, prediction_type=prediction_type)

3
backend/nn/t5.py
View File

@@ -2,11 +2,12 @@ import torch
import math
from backend.attention import attention_pytorch as attention_function
from transformers.activations import NewGELUActivation
activations = {
"gelu_pytorch_tanh": lambda a: torch.nn.functional.gelu(a, approximate="tanh"),
"relu": torch.nn.functional.relu,
"gelu_new": lambda a: NewGELUActivation()(a)
}

2
backend/text_processing/classic_engine.py
View File

@@ -139,7 +139,7 @@ class ClassicTextProcessingEngine:
if self.return_pooled:
pooled_output = outputs.pooler_output
if self.text_projection:
if self.text_projection and self.embedding_key is not 'clip_l':
pooled_output = self.text_encoder.transformer.text_projection(pooled_output)
z.pooled = pooled_output