ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

comfyanonymous cd930d4e7f pop clip vision keys after loading them.		1 year ago
..
cldm	Cleanup: Remove a bunch of useless files.	1 year ago
extra_samplers	Add a total_steps value to sampler callback.	2 years ago
k_diffusion	Not needed anymore.	1 year ago
ldm	Fix DDIM v-prediction.	1 year ago
sd1_tokenizer	Initial commit.	2 years ago
t2i_adapter	Make t2i adapter work with any latent resolution.	2 years ago
taesd	Refactor previews into one command line argument.	1 year ago
checkpoint_pickle.py	Remove pytorch_lightning dependency.	1 year ago
cli_args.py	Add a --gpu-only argument to keep and run everything on the GPU.	1 year ago
clip_vision.py	pop clip vision keys after loading them.	1 year ago
clip_vision_config_h.json	Add support for unCLIP SD2.x models.	2 years ago
clip_vision_config_vitl.json	Add support for unCLIP SD2.x models.	2 years ago
diffusers_convert.py	Refactor diffusers model convert code to be able to reuse it.	1 year ago
diffusers_load.py	Cleanup: Remove a bunch of useless files.	1 year ago
gligen.py	Lowvram mode for gligen and fix some lowvram issues.	2 years ago
model_base.py	Refactor unCLIP noise augment out of samplers.py	1 year ago
model_management.py	Add a --gpu-only argument to keep and run everything on the GPU.	1 year ago
ops.py	Properly disable weight initialization in clip models.	1 year ago
sample.py	Make nodes map over input lists (#579 )	2 years ago
samplers.py	sampler_cfg_function now uses a dict for the argument.	1 year ago
sd.py	This is not needed anymore and causes issues with alphas_cumprod.	1 year ago
sd1_clip.py	Add a --gpu-only argument to keep and run everything on the GPU.	1 year ago
sd1_clip_config.json	Initial commit.	2 years ago
sd2_clip.py	Some refactoring: from_tokens -> encode_from_tokens	2 years ago
sd2_clip_config.json	Use transformers CLIP instead of open_clip for SD2.x	2 years ago
utils.py	Remove pytorch_lightning dependency.	1 year ago