comfyanonymous/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-28 10:54:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'comfyanonymous:master' into weightedConditionCombine

Browse Source
This commit is contained in:
FizzleDorf
2023-04-20 22:00:50 -04:00
committed by GitHub
parent 132464db38 31e60adb28
commit e2b6dd1666
33 changed files with 3047 additions and 182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

133
nodes.py
View File

@@ -21,16 +21,16 @@ import comfy.utils
import comfy.clip_vision
import model_management
import comfy.model_management
import importlib
import folder_paths
def before_node_execution():
model_management.throw_exception_if_processing_interrupted()
comfy.model_management.throw_exception_if_processing_interrupted()
def interrupt_processing(value=True):
model_management.interrupt_current_processing(value)
comfy.model_management.interrupt_current_processing(value)
MAX_RESOLUTION=8192
@@ -272,7 +272,7 @@ class DiffusersLoader:
model_path = os.path.join(search_path, model_path)
break
return comfy.diffusers_convert.load_diffusers(model_path, fp16=model_management.should_use_fp16(), output_vae=output_vae, output_clip=output_clip, embedding_directory=folder_paths.get_folder_paths("embeddings"))
return comfy.diffusers_convert.load_diffusers(model_path, fp16=comfy.model_management.should_use_fp16(), output_vae=output_vae, output_clip=output_clip, embedding_directory=folder_paths.get_folder_paths("embeddings"))
class unCLIPCheckpointLoader:
@@ -521,6 +521,51 @@ class unCLIPConditioning:
c.append(n)
return (c, )
class GLIGENLoader:
@classmethod
def INPUT_TYPES(s):
return {"required": { "gligen_name": (folder_paths.get_filename_list("gligen"), )}}
RETURN_TYPES = ("GLIGEN",)
FUNCTION = "load_gligen"
CATEGORY = "loaders"
def load_gligen(self, gligen_name):
gligen_path = folder_paths.get_full_path("gligen", gligen_name)
gligen = comfy.sd.load_gligen(gligen_path)
return (gligen,)
class GLIGENTextBoxApply:
@classmethod
def INPUT_TYPES(s):
return {"required": {"conditioning_to": ("CONDITIONING", ),
"clip": ("CLIP", ),
"gligen_textbox_model": ("GLIGEN", ),
"text": ("STRING", {"multiline": True}),
"width": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
"height": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
"x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
"y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
}}
RETURN_TYPES = ("CONDITIONING",)
FUNCTION = "append"
CATEGORY = "conditioning/gligen"
def append(self, conditioning_to, clip, gligen_textbox_model, text, width, height, x, y):
c = []
cond, cond_pooled = clip.encode_from_tokens(clip.tokenize(text), return_pooled=True)
for t in conditioning_to:
n = [t[0], t[1].copy()]
position_params = [(cond_pooled, height // 8, width // 8, y // 8, x // 8)]
prev = []
if "gligen" in n[1]:
prev = n[1]['gligen'][2]
n[1]['gligen'] = ("position", gligen_textbox_model, prev + position_params)
c.append(n)
return (c, )
class EmptyLatentImage:
def __init__(self, device="cpu"):
@@ -541,6 +586,24 @@ class EmptyLatentImage:
return ({"samples":latent}, )
class LatentFromBatch:
@classmethod
def INPUT_TYPES(s):
return {"required": { "samples": ("LATENT",),
"batch_index": ("INT", {"default": 0, "min": 0, "max": 63}),
}}
RETURN_TYPES = ("LATENT",)
FUNCTION = "rotate"
CATEGORY = "latent"
def rotate(self, samples, batch_index):
s = samples.copy()
s_in = samples["samples"]
batch_index = min(s_in.shape[0] - 1, batch_index)
s["samples"] = s_in[batch_index:batch_index + 1].clone()
s["batch_index"] = batch_index
return (s,)
class LatentUpscale:
upscale_methods = ["nearest-exact", "bilinear", "area"]
@@ -711,12 +774,19 @@ class SetLatentNoiseMask:
def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False):
latent_image = latent["samples"]
noise_mask = None
device = model_management.get_torch_device()
device = comfy.model_management.get_torch_device()
if disable_noise:
noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
else:
noise = torch.randn(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, generator=torch.manual_seed(seed), device="cpu")
batch_index = 0
if "batch_index" in latent:
batch_index = latent["batch_index"]
generator = torch.manual_seed(seed)
for i in range(batch_index):
noise = torch.randn([1] + list(latent_image.size())[1:], dtype=latent_image.dtype, layout=latent_image.layout, generator=generator, device="cpu")
noise = torch.randn(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, generator=generator, device="cpu")
if "noise_mask" in latent:
noise_mask = latent['noise_mask']
@@ -727,7 +797,7 @@ def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive,
noise_mask = noise_mask.to(device)
real_model = None
model_management.load_model_gpu(model)
comfy.model_management.load_model_gpu(model)
real_model = model.model
noise = noise.to(device)
@@ -737,27 +807,30 @@ def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive,
negative_copy = []
control_nets = []
def get_models(cond):
models = []
for c in cond:
if 'control' in c[1]:
models += [c[1]['control']]
if 'gligen' in c[1]:
models += [c[1]['gligen'][1]]
return models
for p in positive:
t = p[0]
if t.shape[0] < noise.shape[0]:
t = torch.cat([t] * noise.shape[0])
t = t.to(device)
if 'control' in p[1]:
control_nets += [p[1]['control']]
positive_copy += [[t] + p[1:]]
for n in negative:
t = n[0]
if t.shape[0] < noise.shape[0]:
t = torch.cat([t] * noise.shape[0])
t = t.to(device)
if 'control' in n[1]:
control_nets += [n[1]['control']]
negative_copy += [[t] + n[1:]]
control_net_models = []
for x in control_nets:
control_net_models += x.get_control_models()
model_management.load_controlnet_gpu(control_net_models)
models = get_models(positive) + get_models(negative)
comfy.model_management.load_controlnet_gpu(models)
if sampler_name in comfy.samplers.KSampler.SAMPLERS:
sampler = comfy.samplers.KSampler(real_model, steps=steps, device=device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
@@ -767,8 +840,8 @@ def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive,
samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask)
samples = samples.cpu()
for c in control_nets:
c.cleanup()
for m in models:
m.cleanup()
out = latent.copy()
out["samples"] = samples
@@ -902,7 +975,7 @@ class SaveImage:
"filename": file,
"subfolder": subfolder,
"type": self.type
});
})
counter += 1
return { "ui": { "images": results } }
@@ -963,7 +1036,7 @@ class LoadImageMask:
"channel": (["alpha", "red", "green", "blue"], ),}
}
CATEGORY = "image"
CATEGORY = "mask"
RETURN_TYPES = ("MASK",)
FUNCTION = "load_image"
@@ -1104,6 +1177,7 @@ NODE_CLASS_MAPPINGS = {
"VAELoader": VAELoader,
"EmptyLatentImage": EmptyLatentImage,
"LatentUpscale": LatentUpscale,
"LatentFromBatch": LatentFromBatch,
"SaveImage": SaveImage,
"PreviewImage": PreviewImage,
"LoadImage": LoadImage,
@@ -1134,6 +1208,9 @@ NODE_CLASS_MAPPINGS = {
"VAEEncodeTiled": VAEEncodeTiled,
"TomePatchModel": TomePatchModel,
"unCLIPCheckpointLoader": unCLIPCheckpointLoader,
"GLIGENLoader": GLIGENLoader,
"GLIGENTextBoxApply": GLIGENTextBoxApply,
"CheckpointLoader": CheckpointLoader,
"DiffusersLoader": DiffusersLoader,
}
@@ -1211,17 +1288,19 @@ def load_custom_node(module_path):
print(f"Cannot import {module_path} module for custom nodes:", e)
def load_custom_nodes():
CUSTOM_NODE_PATH = os.path.join(os.path.dirname(os.path.realpath(__file__)), "custom_nodes")
possible_modules = os.listdir(CUSTOM_NODE_PATH)
if "__pycache__" in possible_modules:
possible_modules.remove("__pycache__")
node_paths = folder_paths.get_folder_paths("custom_nodes")
for custom_node_path in node_paths:
possible_modules = os.listdir(custom_node_path)
if "__pycache__" in possible_modules:
possible_modules.remove("__pycache__")
for possible_module in possible_modules:
module_path = os.path.join(CUSTOM_NODE_PATH, possible_module)
if os.path.isfile(module_path) and os.path.splitext(module_path)[1] != ".py": continue
load_custom_node(module_path)
for possible_module in possible_modules:
module_path = os.path.join(custom_node_path, possible_module)
if os.path.isfile(module_path) and os.path.splitext(module_path)[1] != ".py": continue
load_custom_node(module_path)
def init_custom_nodes():
load_custom_nodes()
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_upscale_model.py"))
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_post_processing.py"))
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_mask.py"))