mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-01-27 06:40:16 +08:00
Merge remote-tracking branch 'upstream/master' into seedControls
merging
This commit is contained in:
FizzleDorf
commit
e3657c7460
@ -25,3 +25,7 @@ To update the ComfyUI code: update\update_comfyui.bat
|
||||
To update ComfyUI with the python dependencies, note that you should ONLY run this if you have issues with python dependencies.
|
||||
update\update_comfyui_and_python_dependencies.bat
|
||||
|
||||
|
||||
TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
|
||||
In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
|
||||
Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.
|
||||
|
||||
12
README.md
12
README.md
@ -30,6 +30,11 @@ This ui will let you design and execute advanced stable diffusion pipelines usin
|
||||
|
||||
Workflow examples can be found on the [Examples page](https://comfyanonymous.github.io/ComfyUI_examples/)
|
||||
|
||||
## Shortcuts
|
||||
- **Ctrl + A** select all nodes
|
||||
- **Ctrl + M** mute/unmute selected nodes
|
||||
- **Delete** or **Backspace** delete selected nodes
|
||||
|
||||
# Installing
|
||||
|
||||
## Windows
|
||||
@ -40,6 +45,10 @@ There is a portable standalone build for Windows that should work for running on
|
||||
|
||||
Just download, extract and run. Make sure you put your Stable Diffusion checkpoints/models (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints
|
||||
|
||||
#### How do I share models between another UI and ComfyUI?
|
||||
|
||||
See the [Config file](extra_model_paths.yaml.example) to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.
|
||||
|
||||
## Colab Notebook
|
||||
|
||||
To run it on colab or paperspace you can use my [Colab Notebook](notebooks/comfyui_colab.ipynb) here: [Link to open with google colab](https://colab.research.google.com/github/comfyanonymous/ComfyUI/blob/master/notebooks/comfyui_colab.ipynb)
|
||||
@ -64,7 +73,7 @@ AMD users can install rocm and pytorch with pip if you don't have it already ins
|
||||
|
||||
Nvidia users should install torch and xformers using this command:
|
||||
|
||||
```pip install torch==1.13.1 torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu117 xformers```
|
||||
```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118 xformers```
|
||||
|
||||
#### Troubleshooting
|
||||
|
||||
@ -97,7 +106,6 @@ With cmd.exe: ```"path_to_other_sd_gui\venv\Scripts\activate.bat"```
|
||||
|
||||
And then you can use that terminal to run Comfyui without installing any dependencies. Note that the venv folder might be called something else depending on the SD UI.
|
||||
|
||||
|
||||
# Running
|
||||
|
||||
```python main.py```
|
||||
|
||||
@ -78,7 +78,7 @@ class DDIMSampler(object):
|
||||
dynamic_threshold=None,
|
||||
ucg_schedule=None,
|
||||
denoise_function=None,
|
||||
cond_concat=None,
|
||||
extra_args=None,
|
||||
to_zero=True,
|
||||
end_step=None,
|
||||
**kwargs
|
||||
@ -101,7 +101,7 @@ class DDIMSampler(object):
|
||||
dynamic_threshold=dynamic_threshold,
|
||||
ucg_schedule=ucg_schedule,
|
||||
denoise_function=denoise_function,
|
||||
cond_concat=cond_concat,
|
||||
extra_args=extra_args,
|
||||
to_zero=to_zero,
|
||||
end_step=end_step
|
||||
)
|
||||
@ -174,7 +174,7 @@ class DDIMSampler(object):
|
||||
dynamic_threshold=dynamic_threshold,
|
||||
ucg_schedule=ucg_schedule,
|
||||
denoise_function=None,
|
||||
cond_concat=None
|
||||
extra_args=None
|
||||
)
|
||||
return samples, intermediates
|
||||
|
||||
@ -185,7 +185,7 @@ class DDIMSampler(object):
|
||||
mask=None, x0=None, img_callback=None, log_every_t=100,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None, dynamic_threshold=None,
|
||||
ucg_schedule=None, denoise_function=None, cond_concat=None, to_zero=True, end_step=None):
|
||||
ucg_schedule=None, denoise_function=None, extra_args=None, to_zero=True, end_step=None):
|
||||
device = self.model.betas.device
|
||||
b = shape[0]
|
||||
if x_T is None:
|
||||
@ -225,7 +225,7 @@ class DDIMSampler(object):
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
dynamic_threshold=dynamic_threshold, denoise_function=denoise_function, cond_concat=cond_concat)
|
||||
dynamic_threshold=dynamic_threshold, denoise_function=denoise_function, extra_args=extra_args)
|
||||
img, pred_x0 = outs
|
||||
if callback: callback(i)
|
||||
if img_callback: img_callback(pred_x0, i)
|
||||
@ -249,11 +249,11 @@ class DDIMSampler(object):
|
||||
def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None,
|
||||
dynamic_threshold=None, denoise_function=None, cond_concat=None):
|
||||
dynamic_threshold=None, denoise_function=None, extra_args=None):
|
||||
b, *_, device = *x.shape, x.device
|
||||
|
||||
if denoise_function is not None:
|
||||
model_output = denoise_function(self.model.apply_model, x, t, unconditional_conditioning, c, unconditional_guidance_scale, cond_concat)
|
||||
model_output = denoise_function(self.model.apply_model, x, t, **extra_args)
|
||||
elif unconditional_conditioning is None or unconditional_guidance_scale == 1.:
|
||||
model_output = self.model.apply_model(x, t, c)
|
||||
else:
|
||||
|
||||
@ -1317,12 +1317,12 @@ class DiffusionWrapper(torch.nn.Module):
|
||||
self.conditioning_key = conditioning_key
|
||||
assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm', 'hybrid-adm', 'crossattn-adm']
|
||||
|
||||
def forward(self, x, t, c_concat: list = None, c_crossattn: list = None, c_adm=None, control=None):
|
||||
def forward(self, x, t, c_concat: list = None, c_crossattn: list = None, c_adm=None, control=None, transformer_options={}):
|
||||
if self.conditioning_key is None:
|
||||
out = self.diffusion_model(x, t, control=control)
|
||||
out = self.diffusion_model(x, t, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'concat':
|
||||
xc = torch.cat([x] + c_concat, dim=1)
|
||||
out = self.diffusion_model(xc, t, control=control)
|
||||
out = self.diffusion_model(xc, t, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'crossattn':
|
||||
if not self.sequential_cross_attn:
|
||||
cc = torch.cat(c_crossattn, 1)
|
||||
@ -1332,25 +1332,25 @@ class DiffusionWrapper(torch.nn.Module):
|
||||
# TorchScript changes names of the arguments
|
||||
# with argument cc defined as context=cc scripted model will produce
|
||||
# an error: RuntimeError: forward() is missing value for argument 'argument_3'.
|
||||
out = self.scripted_diffusion_model(x, t, cc, control=control)
|
||||
out = self.scripted_diffusion_model(x, t, cc, control=control, transformer_options=transformer_options)
|
||||
else:
|
||||
out = self.diffusion_model(x, t, context=cc, control=control)
|
||||
out = self.diffusion_model(x, t, context=cc, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'hybrid':
|
||||
xc = torch.cat([x] + c_concat, dim=1)
|
||||
cc = torch.cat(c_crossattn, 1)
|
||||
out = self.diffusion_model(xc, t, context=cc, control=control)
|
||||
out = self.diffusion_model(xc, t, context=cc, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'hybrid-adm':
|
||||
assert c_adm is not None
|
||||
xc = torch.cat([x] + c_concat, dim=1)
|
||||
cc = torch.cat(c_crossattn, 1)
|
||||
out = self.diffusion_model(xc, t, context=cc, y=c_adm, control=control)
|
||||
out = self.diffusion_model(xc, t, context=cc, y=c_adm, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'crossattn-adm':
|
||||
assert c_adm is not None
|
||||
cc = torch.cat(c_crossattn, 1)
|
||||
out = self.diffusion_model(x, t, context=cc, y=c_adm, control=control)
|
||||
out = self.diffusion_model(x, t, context=cc, y=c_adm, control=control, transformer_options=transformer_options)
|
||||
elif self.conditioning_key == 'adm':
|
||||
cc = c_crossattn[0]
|
||||
out = self.diffusion_model(x, t, y=cc, control=control)
|
||||
out = self.diffusion_model(x, t, y=cc, control=control, transformer_options=transformer_options)
|
||||
else:
|
||||
raise NotImplementedError()
|
||||
|
||||
|
||||
@ -504,10 +504,10 @@ class BasicTransformerBlock(nn.Module):
|
||||
self.norm3 = nn.LayerNorm(dim)
|
||||
self.checkpoint = checkpoint
|
||||
|
||||
def forward(self, x, context=None):
|
||||
return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
|
||||
def forward(self, x, context=None, transformer_options={}):
|
||||
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
|
||||
|
||||
def _forward(self, x, context=None):
|
||||
def _forward(self, x, context=None, transformer_options={}):
|
||||
x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
|
||||
x = self.attn2(self.norm2(x), context=context) + x
|
||||
x = self.ff(self.norm3(x)) + x
|
||||
@ -557,7 +557,7 @@ class SpatialTransformer(nn.Module):
|
||||
self.proj_out = zero_module(nn.Linear(in_channels, inner_dim))
|
||||
self.use_linear = use_linear
|
||||
|
||||
def forward(self, x, context=None):
|
||||
def forward(self, x, context=None, transformer_options={}):
|
||||
# note: if no context is given, cross-attention defaults to self-attention
|
||||
if not isinstance(context, list):
|
||||
context = [context]
|
||||
@ -570,7 +570,7 @@ class SpatialTransformer(nn.Module):
|
||||
if self.use_linear:
|
||||
x = self.proj_in(x)
|
||||
for i, block in enumerate(self.transformer_blocks):
|
||||
x = block(x, context=context[i])
|
||||
x = block(x, context=context[i], transformer_options=transformer_options)
|
||||
if self.use_linear:
|
||||
x = self.proj_out(x)
|
||||
x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w).contiguous()
|
||||
|
||||
@ -76,12 +76,12 @@ class TimestepEmbedSequential(nn.Sequential, TimestepBlock):
|
||||
support it as an extra input.
|
||||
"""
|
||||
|
||||
def forward(self, x, emb, context=None):
|
||||
def forward(self, x, emb, context=None, transformer_options={}):
|
||||
for layer in self:
|
||||
if isinstance(layer, TimestepBlock):
|
||||
x = layer(x, emb)
|
||||
elif isinstance(layer, SpatialTransformer):
|
||||
x = layer(x, context)
|
||||
x = layer(x, context, transformer_options)
|
||||
else:
|
||||
x = layer(x)
|
||||
return x
|
||||
@ -753,7 +753,7 @@ class UNetModel(nn.Module):
|
||||
self.middle_block.apply(convert_module_to_f32)
|
||||
self.output_blocks.apply(convert_module_to_f32)
|
||||
|
||||
def forward(self, x, timesteps=None, context=None, y=None, control=None, **kwargs):
|
||||
def forward(self, x, timesteps=None, context=None, y=None, control=None, transformer_options={}, **kwargs):
|
||||
"""
|
||||
Apply the model to an input batch.
|
||||
:param x: an [N x C x ...] Tensor of inputs.
|
||||
@ -762,6 +762,7 @@ class UNetModel(nn.Module):
|
||||
:param y: an [N] Tensor of labels, if class-conditional.
|
||||
:return: an [N x C x ...] Tensor of outputs.
|
||||
"""
|
||||
transformer_options["original_shape"] = list(x.shape)
|
||||
assert (y is not None) == (
|
||||
self.num_classes is not None
|
||||
), "must specify y if and only if the model is class-conditional"
|
||||
@ -775,13 +776,13 @@ class UNetModel(nn.Module):
|
||||
|
||||
h = x.type(self.dtype)
|
||||
for id, module in enumerate(self.input_blocks):
|
||||
h = module(h, emb, context)
|
||||
h = module(h, emb, context, transformer_options)
|
||||
if control is not None and 'input' in control and len(control['input']) > 0:
|
||||
ctrl = control['input'].pop()
|
||||
if ctrl is not None:
|
||||
h += ctrl
|
||||
hs.append(h)
|
||||
h = self.middle_block(h, emb, context)
|
||||
h = self.middle_block(h, emb, context, transformer_options)
|
||||
if control is not None and 'middle' in control and len(control['middle']) > 0:
|
||||
h += control['middle'].pop()
|
||||
|
||||
@ -793,7 +794,7 @@ class UNetModel(nn.Module):
|
||||
hsp += ctrl
|
||||
h = th.cat([h, hsp], dim=1)
|
||||
del hsp
|
||||
h = module(h, emb, context)
|
||||
h = module(h, emb, context, transformer_options)
|
||||
h = h.type(x.dtype)
|
||||
if self.predict_codebook_ids:
|
||||
return self.id_predictor(h)
|
||||
|
||||
@ -26,7 +26,7 @@ class CFGDenoiser(torch.nn.Module):
|
||||
|
||||
#The main sampling function shared by all the samplers
|
||||
#Returns predicted noise
|
||||
def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, cond_concat=None):
|
||||
def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, cond_concat=None, model_options={}):
|
||||
def get_area_and_mult(cond, x_in, cond_concat_in, timestep_in):
|
||||
area = (x_in.shape[2], x_in.shape[3], 0, 0)
|
||||
strength = 1.0
|
||||
@ -169,6 +169,9 @@ def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, con
|
||||
if control is not None:
|
||||
c['control'] = control.get_control(input_x, timestep_, c['c_crossattn'], len(cond_or_uncond))
|
||||
|
||||
if 'transformer_options' in model_options:
|
||||
c['transformer_options'] = model_options['transformer_options']
|
||||
|
||||
output = model_function(input_x, timestep_, cond=c).chunk(batch_chunks)
|
||||
del input_x
|
||||
|
||||
@ -221,7 +224,7 @@ class KSamplerX0Inpaint(torch.nn.Module):
|
||||
def forward(self, x, sigma, uncond, cond, cond_scale, denoise_mask, cond_concat=None):
|
||||
if denoise_mask is not None:
|
||||
latent_mask = 1. - denoise_mask
|
||||
x = x * denoise_mask + (self.latent_image + self.noise * sigma) * latent_mask
|
||||
x = x * denoise_mask + (self.latent_image + self.noise * sigma.reshape([sigma.shape[0]] + [1] * (len(self.noise.shape) - 1))) * latent_mask
|
||||
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat)
|
||||
if denoise_mask is not None:
|
||||
out *= denoise_mask
|
||||
@ -242,7 +245,10 @@ def ddim_scheduler(model, steps):
|
||||
sigs = []
|
||||
ddim_timesteps = make_ddim_timesteps(ddim_discr_method="uniform", num_ddim_timesteps=steps, num_ddpm_timesteps=model.inner_model.inner_model.num_timesteps, verbose=False)
|
||||
for x in range(len(ddim_timesteps) - 1, -1, -1):
|
||||
sigs.append(model.t_to_sigma(torch.tensor(ddim_timesteps[x])))
|
||||
ts = ddim_timesteps[x]
|
||||
if ts > 999:
|
||||
ts = 999
|
||||
sigs.append(model.t_to_sigma(torch.tensor(ts)))
|
||||
sigs += [0.0]
|
||||
return torch.FloatTensor(sigs)
|
||||
|
||||
@ -373,7 +379,7 @@ class KSampler:
|
||||
|
||||
def set_steps(self, steps, denoise=None):
|
||||
self.steps = steps
|
||||
if denoise is None:
|
||||
if denoise is None or denoise > 0.9999:
|
||||
self.sigmas = self._calculate_sigmas(steps)
|
||||
else:
|
||||
new_steps = int(steps/denoise)
|
||||
@ -464,7 +470,7 @@ class KSampler:
|
||||
x_T=z_enc,
|
||||
x0=latent_image,
|
||||
denoise_function=sampling_function,
|
||||
cond_concat=cond_concat,
|
||||
extra_args=extra_args,
|
||||
mask=noise_mask,
|
||||
to_zero=sigmas[-1]==0,
|
||||
end_step=sigmas.shape[0] - 1)
|
||||
|
||||
11
comfy/sd.py
11
comfy/sd.py
@ -439,9 +439,14 @@ class VAE:
|
||||
model_management.unload_model()
|
||||
self.first_stage_model = self.first_stage_model.to(self.device)
|
||||
try:
|
||||
samples = samples_in.to(self.device)
|
||||
pixel_samples = self.first_stage_model.decode(1. / self.scale_factor * samples)
|
||||
pixel_samples = torch.clamp((pixel_samples + 1.0) / 2.0, min=0.0, max=1.0)
|
||||
free_memory = model_management.get_free_memory(self.device)
|
||||
batch_number = int((free_memory * 0.7) / (2562 * samples_in.shape[2] * samples_in.shape[3] * 64))
|
||||
batch_number = max(1, batch_number)
|
||||
|
||||
pixel_samples = torch.empty((samples_in.shape[0], 3, round(samples_in.shape[2] * 8), round(samples_in.shape[3] * 8)), device="cpu")
|
||||
for x in range(0, samples_in.shape[0], batch_number):
|
||||
samples = samples_in[x:x+batch_number].to(self.device)
|
||||
pixel_samples[x:x+batch_number] = torch.clamp((self.first_stage_model.decode(1. / self.scale_factor * samples) + 1.0) / 2.0, min=0.0, max=1.0).cpu()
|
||||
except model_management.OOM_EXCEPTION as e:
|
||||
print("Warning: Ran out of memory when regular VAE decoding, retrying with tiled VAE decoding.")
|
||||
pixel_samples = self.decode_tiled_(samples_in)
|
||||
|
||||
15
execution.py
15
execution.py
@ -10,7 +10,7 @@ import gc
|
||||
import torch
|
||||
import nodes
|
||||
|
||||
def get_input_data(inputs, class_def, outputs={}, prompt={}, extra_data={}):
|
||||
def get_input_data(inputs, class_def, unique_id, outputs={}, prompt={}, extra_data={}):
|
||||
valid_inputs = class_def.INPUT_TYPES()
|
||||
input_data_all = {}
|
||||
for x in inputs:
|
||||
@ -34,6 +34,8 @@ def get_input_data(inputs, class_def, outputs={}, prompt={}, extra_data={}):
|
||||
if h[x] == "EXTRA_PNGINFO":
|
||||
if "extra_pnginfo" in extra_data:
|
||||
input_data_all[x] = extra_data['extra_pnginfo']
|
||||
if h[x] == "UNIQUE_ID":
|
||||
input_data_all[x] = unique_id
|
||||
return input_data_all
|
||||
|
||||
def recursive_execute(server, prompt, outputs, current_item, extra_data={}):
|
||||
@ -55,7 +57,7 @@ def recursive_execute(server, prompt, outputs, current_item, extra_data={}):
|
||||
if input_unique_id not in outputs:
|
||||
executed += recursive_execute(server, prompt, outputs, input_unique_id, extra_data)
|
||||
|
||||
input_data_all = get_input_data(inputs, class_def, outputs, prompt, extra_data)
|
||||
input_data_all = get_input_data(inputs, class_def, unique_id, outputs, prompt, extra_data)
|
||||
if server.client_id is not None:
|
||||
server.last_node_id = unique_id
|
||||
server.send_sync("executing", { "node": unique_id }, server.client_id)
|
||||
@ -63,8 +65,11 @@ def recursive_execute(server, prompt, outputs, current_item, extra_data={}):
|
||||
|
||||
nodes.before_node_execution()
|
||||
outputs[unique_id] = getattr(obj, obj.FUNCTION)(**input_data_all)
|
||||
if "ui" in outputs[unique_id] and server.client_id is not None:
|
||||
server.send_sync("executed", { "node": unique_id, "output": outputs[unique_id]["ui"] }, server.client_id)
|
||||
if "ui" in outputs[unique_id]:
|
||||
if server.client_id is not None:
|
||||
server.send_sync("executed", { "node": unique_id, "output": outputs[unique_id]["ui"] }, server.client_id)
|
||||
if "result" in outputs[unique_id]:
|
||||
outputs[unique_id] = outputs[unique_id]["result"]
|
||||
return executed + [unique_id]
|
||||
|
||||
def recursive_will_execute(prompt, outputs, current_item):
|
||||
@ -96,7 +101,7 @@ def recursive_output_delete_if_changed(prompt, old_prompt, outputs, current_item
|
||||
if unique_id in old_prompt and 'is_changed' in old_prompt[unique_id]:
|
||||
is_changed_old = old_prompt[unique_id]['is_changed']
|
||||
if 'is_changed' not in prompt[unique_id]:
|
||||
input_data_all = get_input_data(inputs, class_def, outputs)
|
||||
input_data_all = get_input_data(inputs, class_def, unique_id, outputs)
|
||||
if input_data_all is not None:
|
||||
is_changed = class_def.IS_CHANGED(**input_data_all)
|
||||
prompt[unique_id]['is_changed'] = is_changed
|
||||
|
||||
23
main.py
23
main.py
@ -12,12 +12,13 @@ if os.name == "nt":
|
||||
if __name__ == "__main__":
|
||||
if '--help' in sys.argv:
|
||||
print("Valid Command line Arguments:")
|
||||
print("\t--listen\t\t\tListen on 0.0.0.0 so the UI can be accessed from other computers.")
|
||||
print("\t--listen [ip]\t\t\tListen on ip or 0.0.0.0 if none given so the UI can be accessed from other computers.")
|
||||
print("\t--port 8188\t\t\tSet the listen port.")
|
||||
print("\t--dont-upcast-attention\t\tDisable upcasting of attention \n\t\t\t\t\tcan boost speed but increase the chances of black images.\n")
|
||||
print("\t--use-split-cross-attention\tUse the split cross attention optimization instead of the sub-quadratic one.\n\t\t\t\t\tIgnored when xformers is used.")
|
||||
print("\t--use-pytorch-cross-attention\tUse the new pytorch 2.0 cross attention function.")
|
||||
print("\t--disable-xformers\t\tdisables xformers")
|
||||
print("\t--cuda-device 1\t\tSet the id of the cuda device this instance will use.")
|
||||
print()
|
||||
print("\t--highvram\t\t\tBy default models will be unloaded to CPU memory after being used.\n\t\t\t\t\tThis option keeps them in GPU memory.\n")
|
||||
print("\t--normalvram\t\t\tUsed to force normal vram use if lowvram gets automatically enabled.")
|
||||
@ -31,6 +32,14 @@ if __name__ == "__main__":
|
||||
print("disabling upcasting of attention")
|
||||
os.environ['ATTN_PRECISION'] = "fp16"
|
||||
|
||||
try:
|
||||
index = sys.argv.index('--cuda-device')
|
||||
device = sys.argv[index + 1]
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = device
|
||||
print("Set cuda device to:", device)
|
||||
except:
|
||||
pass
|
||||
|
||||
import execution
|
||||
import server
|
||||
import folder_paths
|
||||
@ -92,11 +101,19 @@ if __name__ == "__main__":
|
||||
hijack_progress(server)
|
||||
|
||||
threading.Thread(target=prompt_worker, daemon=True, args=(q,server,)).start()
|
||||
if '--listen' in sys.argv:
|
||||
try:
|
||||
address = '0.0.0.0'
|
||||
else:
|
||||
p_index = sys.argv.index('--listen')
|
||||
try:
|
||||
ip = sys.argv[p_index + 1]
|
||||
if ip[:2] != '--':
|
||||
address = ip
|
||||
except:
|
||||
pass
|
||||
except:
|
||||
address = '127.0.0.1'
|
||||
|
||||
|
||||
dont_print = False
|
||||
if '--dont-print-server' in sys.argv:
|
||||
dont_print = True
|
||||
|
||||
@ -47,7 +47,7 @@
|
||||
" !git pull\n",
|
||||
"\n",
|
||||
"!echo -= Install dependencies =-\n",
|
||||
"!pip -q install xformers -r requirements.txt"
|
||||
"!pip install xformers==0.0.16 -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu117"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@ -3,7 +3,7 @@ torchdiffeq
|
||||
torchsde
|
||||
einops
|
||||
open-clip-torch
|
||||
transformers
|
||||
transformers>=4.25.1
|
||||
safetensors
|
||||
pytorch_lightning
|
||||
aiohttp
|
||||
|
||||
351
web/extensions/core/colorPalette.js
Normal file
351
web/extensions/core/colorPalette.js
Normal file
@ -0,0 +1,351 @@
|
||||
import { app } from "/scripts/app.js";
|
||||
import { $el } from "/scripts/ui.js";
|
||||
import { api } from "/scripts/api.js";
|
||||
|
||||
// Manage color palettes
|
||||
|
||||
const colorPalettes = {
|
||||
"palette_1": {
|
||||
"id": "palette_1",
|
||||
"name": "Palette 1",
|
||||
"colors": {
|
||||
"node_slot": {
|
||||
"CLIP": "#FFD500", // bright yellow
|
||||
"CLIP_VISION": "#A8DADC", // light blue-gray
|
||||
"CLIP_VISION_OUTPUT": "#ad7452", // rusty brown-orange
|
||||
"CONDITIONING": "#FFA931", // vibrant orange-yellow
|
||||
"CONTROL_NET": "#6EE7B7", // soft mint green
|
||||
"IMAGE": "#64B5F6", // bright sky blue
|
||||
"LATENT": "#FF9CF9", // light pink-purple
|
||||
"MASK": "#81C784", // muted green
|
||||
"MODEL": "#B39DDB", // light lavender-purple
|
||||
"STYLE_MODEL": "#C2FFAE", // light green-yellow
|
||||
"VAE": "#FF6E6E", // bright red
|
||||
}
|
||||
}
|
||||
},
|
||||
"palette_2": {
|
||||
"id": "palette_2",
|
||||
"name": "Palette 2",
|
||||
"colors": {
|
||||
"node_slot": {
|
||||
"CLIP": "#556B2F", // Dark Olive Green
|
||||
"CLIP_VISION": "#4B0082", // Indigo
|
||||
"CLIP_VISION_OUTPUT": "#006400", // Green
|
||||
"CONDITIONING": "#FF1493", // Deep Pink
|
||||
"CONTROL_NET": "#8B4513", // Saddle Brown
|
||||
"IMAGE": "#8B0000", // Dark Red
|
||||
"LATENT": "#00008B", // Dark Blue
|
||||
"MASK": "#2F4F4F", // Dark Slate Grey
|
||||
"MODEL": "#FF8C00", // Dark Orange
|
||||
"STYLE_MODEL": "#004A4A", // Sherpa Blue
|
||||
"UPSCALE_MODEL": "#4A004A", // Tyrian Purple
|
||||
"VAE": "#4F394F", // Loulou
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const id = "Comfy.ColorPalette";
|
||||
const idCustomColorPalettes = "Comfy.CustomColorPalettes";
|
||||
const defaultColorPaletteId = "palette_1";
|
||||
const els = {}
|
||||
// const ctxMenu = LiteGraph.ContextMenu;
|
||||
app.registerExtension({
|
||||
name: id,
|
||||
init() {
|
||||
const sortObjectKeys = (unordered) => {
|
||||
return Object.keys(unordered).sort().reduce((obj, key) => {
|
||||
obj[key] = unordered[key];
|
||||
return obj;
|
||||
}, {});
|
||||
};
|
||||
|
||||
const getSlotTypes = async () => {
|
||||
var types = [];
|
||||
|
||||
const defs = await api.getNodeDefs();
|
||||
for (const nodeId in defs) {
|
||||
const nodeData = defs[nodeId];
|
||||
|
||||
var inputs = nodeData["input"]["required"];
|
||||
if (nodeData["input"]["optional"] != undefined){
|
||||
inputs = Object.assign({}, nodeData["input"]["required"], nodeData["input"]["optional"])
|
||||
}
|
||||
|
||||
for (const inputName in inputs) {
|
||||
const inputData = inputs[inputName];
|
||||
const type = inputData[0];
|
||||
|
||||
if (!Array.isArray(type)) {
|
||||
types.push(type);
|
||||
}
|
||||
}
|
||||
|
||||
for (const o in nodeData["output"]) {
|
||||
const output = nodeData["output"][o];
|
||||
types.push(output);
|
||||
}
|
||||
}
|
||||
|
||||
return types;
|
||||
};
|
||||
|
||||
const completeColorPalette = async (colorPalette) => {
|
||||
var types = await getSlotTypes();
|
||||
|
||||
for (const type of types) {
|
||||
if (!colorPalette.colors.node_slot[type]) {
|
||||
colorPalette.colors.node_slot[type] = "";
|
||||
}
|
||||
}
|
||||
|
||||
colorPalette.colors.node_slot = sortObjectKeys(colorPalette.colors.node_slot);
|
||||
|
||||
return colorPalette;
|
||||
};
|
||||
|
||||
const getColorPaletteTemplate = async () => {
|
||||
let colorPalette = {
|
||||
"id": "my_color_palette_unique_id",
|
||||
"name": "My Color Palette",
|
||||
"colors": {
|
||||
"node_slot": {
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
return completeColorPalette(colorPalette);
|
||||
};
|
||||
|
||||
const getCustomColorPalettes = () => {
|
||||
return app.ui.settings.getSettingValue(idCustomColorPalettes, {});
|
||||
};
|
||||
|
||||
const setCustomColorPalettes = (customColorPalettes) => {
|
||||
return app.ui.settings.setSettingValue(idCustomColorPalettes, customColorPalettes);
|
||||
};
|
||||
|
||||
const addCustomColorPalette = async (colorPalette) => {
|
||||
if (typeof(colorPalette) !== "object") {
|
||||
app.ui.dialog.show("Invalid color palette");
|
||||
return;
|
||||
}
|
||||
|
||||
if (!colorPalette.id) {
|
||||
app.ui.dialog.show("Color palette missing id");
|
||||
return;
|
||||
}
|
||||
|
||||
if (!colorPalette.name) {
|
||||
app.ui.dialog.show("Color palette missing name");
|
||||
return;
|
||||
}
|
||||
|
||||
if (!colorPalette.colors) {
|
||||
app.ui.dialog.show("Color palette missing colors");
|
||||
return;
|
||||
}
|
||||
|
||||
if (colorPalette.colors.node_slot && typeof(colorPalette.colors.node_slot) !== "object") {
|
||||
app.ui.dialog.show("Invalid color palette colors.node_slot");
|
||||
return;
|
||||
}
|
||||
|
||||
let customColorPalettes = getCustomColorPalettes();
|
||||
customColorPalettes[colorPalette.id] = colorPalette;
|
||||
setCustomColorPalettes(customColorPalettes);
|
||||
|
||||
for (const option of els.select.childNodes) {
|
||||
if (option.value === "custom_" + colorPalette.id) {
|
||||
els.select.removeChild(option);
|
||||
}
|
||||
}
|
||||
|
||||
els.select.append($el("option", { textContent: colorPalette.name + " (custom)", value: "custom_" + colorPalette.id, selected: true }));
|
||||
|
||||
setColorPalette("custom_" + colorPalette.id);
|
||||
await loadColorPalette(colorPalette);
|
||||
};
|
||||
|
||||
const deleteCustomColorPalette = async (colorPaletteId) => {
|
||||
let customColorPalettes = getCustomColorPalettes();
|
||||
delete customColorPalettes[colorPaletteId];
|
||||
setCustomColorPalettes(customColorPalettes);
|
||||
|
||||
for (const option of els.select.childNodes) {
|
||||
if (option.value === defaultColorPaletteId) {
|
||||
option.selected = true;
|
||||
}
|
||||
|
||||
if (option.value === "custom_" + colorPaletteId) {
|
||||
els.select.removeChild(option);
|
||||
}
|
||||
}
|
||||
|
||||
setColorPalette(defaultColorPaletteId);
|
||||
await loadColorPalette(getColorPalette());
|
||||
};
|
||||
|
||||
const loadColorPalette = async (colorPalette) => {
|
||||
colorPalette = await completeColorPalette(colorPalette);
|
||||
if (colorPalette.colors) {
|
||||
if (colorPalette.colors.node_slot) {
|
||||
Object.assign(app.canvas.default_connection_color_byType, colorPalette.colors.node_slot);
|
||||
app.canvas.draw(true, true);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const getColorPalette = (colorPaletteId) => {
|
||||
if (!colorPaletteId) {
|
||||
colorPaletteId = app.ui.settings.getSettingValue(id, defaultColorPaletteId);
|
||||
}
|
||||
|
||||
if (colorPaletteId.startsWith("custom_")) {
|
||||
colorPaletteId = colorPaletteId.substr(7);
|
||||
let customColorPalettes = getCustomColorPalettes();
|
||||
if (customColorPalettes[colorPaletteId]) {
|
||||
return customColorPalettes[colorPaletteId];
|
||||
}
|
||||
}
|
||||
|
||||
return colorPalettes[colorPaletteId];
|
||||
};
|
||||
|
||||
const setColorPalette = (colorPaletteId) => {
|
||||
app.ui.settings.setSettingValue(id, colorPaletteId);
|
||||
};
|
||||
|
||||
const fileInput = $el("input", {
|
||||
type: "file",
|
||||
accept: ".json",
|
||||
style: { display: "none" },
|
||||
parent: document.body,
|
||||
onchange: () => {
|
||||
let file = fileInput.files[0];
|
||||
|
||||
if (file.type === "application/json" || file.name.endsWith(".json")) {
|
||||
const reader = new FileReader();
|
||||
reader.onload = async () => {
|
||||
await addCustomColorPalette(JSON.parse(reader.result));
|
||||
};
|
||||
reader.readAsText(file);
|
||||
}
|
||||
},
|
||||
});
|
||||
|
||||
app.ui.settings.addSetting({
|
||||
id,
|
||||
name: "Color Palette",
|
||||
type: (name, setter, value) => {
|
||||
let options = [];
|
||||
|
||||
for (const c in colorPalettes) {
|
||||
const colorPalette = colorPalettes[c];
|
||||
options.push($el("option", { textContent: colorPalette.name, value: colorPalette.id, selected: colorPalette.id === value }));
|
||||
}
|
||||
|
||||
let customColorPalettes = getCustomColorPalettes();
|
||||
for (const c in customColorPalettes) {
|
||||
const colorPalette = customColorPalettes[c];
|
||||
options.push($el("option", { textContent: colorPalette.name + " (custom)", value: "custom_" + colorPalette.id, selected: "custom_" + colorPalette.id === value }));
|
||||
}
|
||||
|
||||
return $el("div", [
|
||||
$el("label", { textContent: name || id }, [
|
||||
els.select = $el("select", {
|
||||
onchange: (e) => {
|
||||
setter(e.target.value);
|
||||
}
|
||||
}, options)
|
||||
]),
|
||||
$el("input", {
|
||||
type: "button",
|
||||
value: "Export",
|
||||
onclick: async () => {
|
||||
const colorPaletteId = app.ui.settings.getSettingValue(id, defaultColorPaletteId);
|
||||
const colorPalette = await completeColorPalette(getColorPalette(colorPaletteId));
|
||||
const json = JSON.stringify(colorPalette, null, 2); // convert the data to a JSON string
|
||||
const blob = new Blob([json], { type: "application/json" });
|
||||
const url = URL.createObjectURL(blob);
|
||||
const a = $el("a", {
|
||||
href: url,
|
||||
download: colorPaletteId + ".json",
|
||||
style: { display: "none" },
|
||||
parent: document.body,
|
||||
});
|
||||
a.click();
|
||||
setTimeout(function () {
|
||||
a.remove();
|
||||
window.URL.revokeObjectURL(url);
|
||||
}, 0);
|
||||
},
|
||||
}),
|
||||
$el("input", {
|
||||
type: "button",
|
||||
value: "Import",
|
||||
onclick: () => {
|
||||
fileInput.click();
|
||||
}
|
||||
}),
|
||||
$el("input", {
|
||||
type: "button",
|
||||
value: "Template",
|
||||
onclick: async () => {
|
||||
const colorPalette = await getColorPaletteTemplate();
|
||||
const json = JSON.stringify(colorPalette, null, 2); // convert the data to a JSON string
|
||||
const blob = new Blob([json], { type: "application/json" });
|
||||
const url = URL.createObjectURL(blob);
|
||||
const a = $el("a", {
|
||||
href: url,
|
||||
download: "color_palette.json",
|
||||
style: { display: "none" },
|
||||
parent: document.body,
|
||||
});
|
||||
a.click();
|
||||
setTimeout(function () {
|
||||
a.remove();
|
||||
window.URL.revokeObjectURL(url);
|
||||
}, 0);
|
||||
}
|
||||
}),
|
||||
$el("input", {
|
||||
type: "button",
|
||||
value: "Delete",
|
||||
onclick: async () => {
|
||||
let colorPaletteId = app.ui.settings.getSettingValue(id, defaultColorPaletteId);
|
||||
|
||||
if (colorPalettes[colorPaletteId]) {
|
||||
app.ui.dialog.show("You cannot delete built-in color palette");
|
||||
return;
|
||||
}
|
||||
|
||||
if (colorPaletteId.startsWith("custom_")) {
|
||||
colorPaletteId = colorPaletteId.substr(7);
|
||||
}
|
||||
|
||||
await deleteCustomColorPalette(colorPaletteId);
|
||||
}
|
||||
}),
|
||||
]);
|
||||
},
|
||||
defaultValue: defaultColorPaletteId,
|
||||
async onChange(value) {
|
||||
if (!value) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (colorPalettes[value]) {
|
||||
await loadColorPalette(colorPalettes[value]);
|
||||
} else if (value.startsWith("custom_")) {
|
||||
value = value.substr(7);
|
||||
let customColorPalettes = getCustomColorPalettes();
|
||||
if (customColorPalettes[value]) {
|
||||
await loadColorPalette(customColorPalettes[value]);
|
||||
}
|
||||
}
|
||||
},
|
||||
});
|
||||
},
|
||||
});
|
||||
100
web/extensions/core/saveImageExtraOutput.js
Normal file
100
web/extensions/core/saveImageExtraOutput.js
Normal file
@ -0,0 +1,100 @@
|
||||
import { app } from "/scripts/app.js";
|
||||
|
||||
// Use widget values and dates in output filenames
|
||||
|
||||
app.registerExtension({
|
||||
name: "Comfy.SaveImageExtraOutput",
|
||||
async beforeRegisterNodeDef(nodeType, nodeData, app) {
|
||||
if (nodeData.name === "SaveImage") {
|
||||
const onNodeCreated = nodeType.prototype.onNodeCreated;
|
||||
|
||||
// Simple date formatter
|
||||
const parts = {
|
||||
d: (d) => d.getDate(),
|
||||
M: (d) => d.getMonth() + 1,
|
||||
h: (d) => d.getHours(),
|
||||
m: (d) => d.getMinutes(),
|
||||
s: (d) => d.getSeconds(),
|
||||
};
|
||||
const format =
|
||||
Object.keys(parts)
|
||||
.map((k) => k + k + "?")
|
||||
.join("|") + "|yyy?y?";
|
||||
|
||||
function formatDate(text, date) {
|
||||
return text.replace(new RegExp(format, "g"), function (text) {
|
||||
if (text === "yy") return (date.getFullYear() + "").substring(2);
|
||||
if (text === "yyyy") return date.getFullYear();
|
||||
if (text[0] in parts) {
|
||||
const p = parts[text[0]](date);
|
||||
return (p + "").padStart(text.length, "0");
|
||||
}
|
||||
return text;
|
||||
});
|
||||
}
|
||||
|
||||
// When the SaveImage node is created we want to override the serialization of the output name widget to run our S&R
|
||||
nodeType.prototype.onNodeCreated = function () {
|
||||
const r = onNodeCreated ? onNodeCreated.apply(this, arguments) : undefined;
|
||||
|
||||
const widget = this.widgets.find((w) => w.name === "filename_prefix");
|
||||
widget.serializeValue = () => {
|
||||
return widget.value.replace(/%([^%]+)%/g, function (match, text) {
|
||||
const split = text.split(".");
|
||||
if (split.length !== 2) {
|
||||
// Special handling for dates
|
||||
if (split[0].startsWith("date:")) {
|
||||
return formatDate(split[0].substring(5), new Date());
|
||||
}
|
||||
|
||||
if (text !== "width" && text !== "height") {
|
||||
// Dont warn on standard replacements
|
||||
console.warn("Invalid replacement pattern", text);
|
||||
}
|
||||
return match;
|
||||
}
|
||||
|
||||
// Find node with matching S&R property name
|
||||
let nodes = app.graph._nodes.filter((n) => n.properties?.["Node name for S&R"] === split[0]);
|
||||
// If we cant, see if there is a node with that title
|
||||
if (!nodes.length) {
|
||||
nodes = app.graph._nodes.filter((n) => n.title === split[0]);
|
||||
}
|
||||
if (!nodes.length) {
|
||||
console.warn("Unable to find node", split[0]);
|
||||
return match;
|
||||
}
|
||||
|
||||
if (nodes.length > 1) {
|
||||
console.warn("Multiple nodes matched", split[0], "using first match");
|
||||
}
|
||||
|
||||
const node = nodes[0];
|
||||
|
||||
const widget = node.widgets?.find((w) => w.name === split[1]);
|
||||
if (!widget) {
|
||||
console.warn("Unable to find widget", split[1], "on node", split[0], node);
|
||||
return match;
|
||||
}
|
||||
|
||||
return ((widget.value ?? "") + "").replaceAll(/\/|\\/g, "_");
|
||||
});
|
||||
};
|
||||
|
||||
return r;
|
||||
};
|
||||
} else {
|
||||
// When any other node is created add a property to alias the node
|
||||
const onNodeCreated = nodeType.prototype.onNodeCreated;
|
||||
nodeType.prototype.onNodeCreated = function () {
|
||||
const r = onNodeCreated ? onNodeCreated.apply(this, arguments) : undefined;
|
||||
|
||||
if (!this.properties || !("Node name for S&R" in this.properties)) {
|
||||
this.addProperty("Node name for S&R", this.title, "string");
|
||||
}
|
||||
|
||||
return r;
|
||||
};
|
||||
}
|
||||
},
|
||||
});
|
||||
@ -105,7 +105,7 @@ app.registerExtension({
|
||||
callback: () => convertToWidget(this, w),
|
||||
});
|
||||
} else {
|
||||
const config = nodeData?.input?.required[w.name] || [w.type, w.options || {}];
|
||||
const config = nodeData?.input?.required[w.name] || nodeData?.input?.optional?.[w.name] || [w.type, w.options || {}];
|
||||
if (isConvertableWidget(w, config)) {
|
||||
toInput.push({
|
||||
content: `Convert ${w.name} to input`,
|
||||
|
||||
@ -417,6 +417,59 @@ class ComfyApp {
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle keypress
|
||||
*
|
||||
* Ctrl + M mute/unmute selected nodes
|
||||
*/
|
||||
#addProcessKeyHandler() {
|
||||
const self = this;
|
||||
const origProcessKey = LGraphCanvas.prototype.processKey;
|
||||
LGraphCanvas.prototype.processKey = function(e) {
|
||||
const res = origProcessKey.apply(this, arguments);
|
||||
|
||||
if (res === false) {
|
||||
return res;
|
||||
}
|
||||
|
||||
if (!this.graph) {
|
||||
return;
|
||||
}
|
||||
|
||||
var block_default = false;
|
||||
|
||||
if (e.target.localName == "input") {
|
||||
return;
|
||||
}
|
||||
|
||||
if (e.type == "keydown") {
|
||||
// Ctrl + M mute/unmute
|
||||
if (e.keyCode == 77 && e.ctrlKey) {
|
||||
if (this.selected_nodes) {
|
||||
for (var i in this.selected_nodes) {
|
||||
if (this.selected_nodes[i].mode === 2) { // never
|
||||
this.selected_nodes[i].mode = 0; // always
|
||||
} else {
|
||||
this.selected_nodes[i].mode = 2; // never
|
||||
}
|
||||
}
|
||||
}
|
||||
block_default = true;
|
||||
}
|
||||
}
|
||||
|
||||
this.graph.change();
|
||||
|
||||
if (block_default) {
|
||||
e.preventDefault();
|
||||
e.stopImmediatePropagation();
|
||||
return false;
|
||||
}
|
||||
|
||||
return res;
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Draws group header bar
|
||||
*/
|
||||
@ -465,10 +518,11 @@ class ComfyApp {
|
||||
* Draws node highlights (executing, drag drop) and progress bar
|
||||
*/
|
||||
#addDrawNodeHandler() {
|
||||
const orig = LGraphCanvas.prototype.drawNodeShape;
|
||||
const origDrawNodeShape = LGraphCanvas.prototype.drawNodeShape;
|
||||
const self = this;
|
||||
|
||||
LGraphCanvas.prototype.drawNodeShape = function (node, ctx, size, fgcolor, bgcolor, selected, mouse_over) {
|
||||
const res = orig.apply(this, arguments);
|
||||
const res = origDrawNodeShape.apply(this, arguments);
|
||||
|
||||
let color = null;
|
||||
if (node.id === +self.runningNodeId) {
|
||||
@ -517,6 +571,21 @@ class ComfyApp {
|
||||
|
||||
return res;
|
||||
};
|
||||
|
||||
const origDrawNode = LGraphCanvas.prototype.drawNode;
|
||||
LGraphCanvas.prototype.drawNode = function (node, ctx) {
|
||||
var editor_alpha = this.editor_alpha;
|
||||
|
||||
if (node.mode === 2) { // never
|
||||
this.editor_alpha = 0.4;
|
||||
}
|
||||
|
||||
const res = origDrawNode.apply(this, arguments);
|
||||
|
||||
this.editor_alpha = editor_alpha;
|
||||
|
||||
return res;
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
@ -548,6 +617,10 @@ class ComfyApp {
|
||||
|
||||
api.addEventListener("executed", ({ detail }) => {
|
||||
this.nodeOutputs[detail.node] = detail.output;
|
||||
const node = this.graph.getNodeById(detail.node);
|
||||
if (node?.onExecuted) {
|
||||
node.onExecuted(detail.output);
|
||||
}
|
||||
});
|
||||
|
||||
api.init();
|
||||
@ -576,27 +649,6 @@ class ComfyApp {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Setup slot colors for types
|
||||
*/
|
||||
setupSlotColors() {
|
||||
let colors = {
|
||||
"CLIP": "#FFD500", // bright yellow
|
||||
"CLIP_VISION": "#A8DADC", // light blue-gray
|
||||
"CLIP_VISION_OUTPUT": "#ad7452", // rusty brown-orange
|
||||
"CONDITIONING": "#FFA931", // vibrant orange-yellow
|
||||
"CONTROL_NET": "#6EE7B7", // soft mint green
|
||||
"IMAGE": "#64B5F6", // bright sky blue
|
||||
"LATENT": "#FF9CF9", // light pink-purple
|
||||
"MASK": "#81C784", // muted green
|
||||
"MODEL": "#B39DDB", // light lavender-purple
|
||||
"STYLE_MODEL": "#C2FFAE", // light green-yellow
|
||||
"VAE": "#FF6E6E", // bright red
|
||||
};
|
||||
|
||||
Object.assign(this.canvas.default_connection_color_byType, colors);
|
||||
}
|
||||
|
||||
/**
|
||||
* Set up the app on the page
|
||||
*/
|
||||
@ -609,13 +661,12 @@ class ComfyApp {
|
||||
document.body.prepend(canvasEl);
|
||||
|
||||
this.#addProcessMouseHandler();
|
||||
this.#addProcessKeyHandler();
|
||||
|
||||
this.graph = new LGraph();
|
||||
const canvas = (this.canvas = new LGraphCanvas(canvasEl, this.graph));
|
||||
this.ctx = canvasEl.getContext("2d");
|
||||
|
||||
this.setupSlotColors();
|
||||
|
||||
this.graph.start();
|
||||
|
||||
function resizeCanvas() {
|
||||
@ -692,18 +743,22 @@ class ComfyApp {
|
||||
const inputData = inputs[inputName];
|
||||
const type = inputData[0];
|
||||
|
||||
if (Array.isArray(type)) {
|
||||
// Enums
|
||||
Object.assign(config, widgets.COMBO(this, inputName, inputData, app) || {});
|
||||
} else if (`${type}:${inputName}` in widgets) {
|
||||
// Support custom widgets by Type:Name
|
||||
Object.assign(config, widgets[`${type}:${inputName}`](this, inputName, inputData, app) || {});
|
||||
} else if (type in widgets) {
|
||||
// Standard type widgets
|
||||
Object.assign(config, widgets[type](this, inputName, inputData, app) || {});
|
||||
} else {
|
||||
// Node connection inputs
|
||||
if(inputData[1]?.forceInput) {
|
||||
this.addInput(inputName, type);
|
||||
} else {
|
||||
if (Array.isArray(type)) {
|
||||
// Enums
|
||||
Object.assign(config, widgets.COMBO(this, inputName, inputData, app) || {});
|
||||
} else if (`${type}:${inputName}` in widgets) {
|
||||
// Support custom widgets by Type:Name
|
||||
Object.assign(config, widgets[`${type}:${inputName}`](this, inputName, inputData, app) || {});
|
||||
} else if (type in widgets) {
|
||||
// Standard type widgets
|
||||
Object.assign(config, widgets[type](this, inputName, inputData, app) || {});
|
||||
} else {
|
||||
// Node connection inputs
|
||||
this.addInput(inputName, type);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -744,6 +799,8 @@ class ComfyApp {
|
||||
* @param {*} graphData A serialized graph object
|
||||
*/
|
||||
loadGraphData(graphData) {
|
||||
this.clean();
|
||||
|
||||
if (!graphData) {
|
||||
graphData = defaultGraph;
|
||||
}
|
||||
@ -802,6 +859,11 @@ class ComfyApp {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (node.mode === 2) {
|
||||
// Don't serialize muted nodes
|
||||
continue;
|
||||
}
|
||||
|
||||
const inputs = {};
|
||||
const widgets = node.widgets;
|
||||
|
||||
@ -841,6 +903,18 @@ class ComfyApp {
|
||||
};
|
||||
}
|
||||
|
||||
// Remove inputs connected to removed nodes
|
||||
|
||||
for (const o in output) {
|
||||
for (const i in output[o].inputs) {
|
||||
if (Array.isArray(output[o].inputs[i])
|
||||
&& output[o].inputs[i].length === 2
|
||||
&& !output[output[o].inputs[i][0]]) {
|
||||
delete output[o].inputs[i];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return { workflow, output };
|
||||
}
|
||||
|
||||
@ -930,6 +1004,13 @@ class ComfyApp {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Clean current state
|
||||
*/
|
||||
clean() {
|
||||
this.nodeOutputs = {};
|
||||
}
|
||||
}
|
||||
|
||||
export const app = new ComfyApp();
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import { api } from "./api.js";
|
||||
|
||||
function $el(tag, propsOrChildren, children) {
|
||||
export function $el(tag, propsOrChildren, children) {
|
||||
const split = tag.split(".");
|
||||
const element = document.createElement(split.shift());
|
||||
element.classList.add(...split);
|
||||
@ -114,6 +114,17 @@ class ComfySettingsDialog extends ComfyDialog {
|
||||
this.settings = [];
|
||||
}
|
||||
|
||||
getSettingValue(id, defaultValue) {
|
||||
const settingId = "Comfy.Settings." + id;
|
||||
const v = localStorage[settingId];
|
||||
return v == null ? defaultValue : JSON.parse(v);
|
||||
}
|
||||
|
||||
setSettingValue(id, value) {
|
||||
const settingId = "Comfy.Settings." + id;
|
||||
localStorage[settingId] = JSON.stringify(value);
|
||||
}
|
||||
|
||||
addSetting({ id, name, type, defaultValue, onChange }) {
|
||||
if (!id) {
|
||||
throw new Error("Settings must have an ID");
|
||||
@ -142,7 +153,7 @@ class ComfySettingsDialog extends ComfyDialog {
|
||||
};
|
||||
|
||||
if (typeof type === "function") {
|
||||
return type(name, setter);
|
||||
return type(name, setter, value);
|
||||
}
|
||||
|
||||
switch (type) {
|
||||
@ -214,10 +225,10 @@ class ComfyList {
|
||||
$el("button", {
|
||||
textContent: "Load",
|
||||
onclick: () => {
|
||||
app.loadGraphData(item.prompt[3].extra_pnginfo.workflow);
|
||||
if (item.outputs) {
|
||||
app.nodeOutputs = item.outputs;
|
||||
}
|
||||
app.loadGraphData(item.prompt[3].extra_pnginfo.workflow);
|
||||
},
|
||||
}),
|
||||
$el("button", {
|
||||
@ -377,7 +388,10 @@ export class ComfyUI {
|
||||
}),
|
||||
$el("button", { textContent: "Load", onclick: () => fileInput.click() }),
|
||||
$el("button", { textContent: "Refresh", onclick: () => app.refreshComboInNodes() }),
|
||||
$el("button", { textContent: "Clear", onclick: () => app.graph.clear() }),
|
||||
$el("button", { textContent: "Clear", onclick: () => {
|
||||
app.clean();
|
||||
app.graph.clear();
|
||||
}}),
|
||||
$el("button", { textContent: "Load Default", onclick: () => app.loadGraphData() }),
|
||||
]);
|
||||
|
||||
|
||||
@ -64,6 +64,12 @@ body {
|
||||
margin-bottom: 20px; /* Add some margin between the text and the close button*/
|
||||
}
|
||||
|
||||
.comfy-modal select,
|
||||
.comfy-modal input[type=button],
|
||||
.comfy-modal input[type=checkbox] {
|
||||
margin: 3px 3px 3px 4px;
|
||||
}
|
||||
|
||||
.comfy-modal button {
|
||||
cursor: pointer;
|
||||
color: #aaaaaa;
|
||||
@ -95,6 +101,12 @@ body {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
color: #999;
|
||||
background-color: #353535;
|
||||
font-family: sans-serif;
|
||||
padding: 10px;
|
||||
border-radius: 0 8px 8px 8px;
|
||||
box-shadow: 3px 3px 8px rgba(0, 0, 0, 0.4);
|
||||
}
|
||||
|
||||
.comfy-menu button {
|
||||
@ -109,6 +121,22 @@ body {
|
||||
.comfy-menu-btns button {
|
||||
font-size: 10px;
|
||||
width: 50%;
|
||||
color: #999 !important;
|
||||
}
|
||||
|
||||
.comfy-menu > button {
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.comfy-menu > button,
|
||||
.comfy-menu-btns button,
|
||||
.comfy-menu .comfy-list button {
|
||||
color: #ddd;
|
||||
background-color: #222;
|
||||
border-radius: 8px;
|
||||
border-color: #4e4e4e;
|
||||
border-style: solid;
|
||||
margin-top: 2px;
|
||||
}
|
||||
|
||||
.comfy-menu span.drag-handle {
|
||||
@ -141,14 +169,18 @@ body {
|
||||
}
|
||||
|
||||
.comfy-list {
|
||||
background-color: rgb(225, 225, 225);
|
||||
color: #999;
|
||||
background-color: #333;
|
||||
margin-bottom: 10px;
|
||||
border-color: #4e4e4e;
|
||||
border-style: solid;
|
||||
}
|
||||
|
||||
.comfy-list-items {
|
||||
overflow-y: scroll;
|
||||
max-height: 100px;
|
||||
background-color: #d0d0d0;
|
||||
min-height: 25px;
|
||||
background-color: #222;
|
||||
padding: 5px;
|
||||
}
|
||||
|
||||
@ -175,6 +207,7 @@ body {
|
||||
}
|
||||
|
||||
button.comfy-settings-btn {
|
||||
background-color: rgba(0, 0, 0, 0);
|
||||
font-size: 12px;
|
||||
padding: 0;
|
||||
position: absolute;
|
||||
@ -182,6 +215,10 @@ button.comfy-settings-btn {
|
||||
border: none;
|
||||
}
|
||||
|
||||
button.comfy-queue-btn {
|
||||
margin: 6px 0 !important;
|
||||
}
|
||||
|
||||
.comfy-modal.comfy-settings {
|
||||
background-color: var(--bg-color);
|
||||
color: var(--fg-color);
|
||||
@ -190,6 +227,13 @@ button.comfy-settings-btn {
|
||||
|
||||
@media only screen and (max-height: 850px) {
|
||||
.comfy-menu {
|
||||
margin-top: -70px;
|
||||
top: 0 !important;
|
||||
bottom: 0 !important;
|
||||
left: auto !important;
|
||||
right: 0 !important;
|
||||
border-radius: 0px;
|
||||
}
|
||||
.comfy-menu span.drag-handle {
|
||||
visibility:hidden
|
||||
}
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user