You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

comfyanonymous fbdb14d4c4 Cleaner CLIP text encoder implementation. ... Use a simple CLIP model implementation instead of the one from transformers. This will allow some interesting things that would too hackish to implement using the transformers implementation.		1 year ago
..
cldm	UNET weights can now be stored in fp8.	1 year ago
extra_samplers	Remove useless argument from uni_pc sampler.	1 year ago
k_diffusion	heunpp2 sampler.	1 year ago
ldm	Cleaner CLIP text encoder implementation.	1 year ago
sd1_tokenizer	Initial commit.	2 years ago
t2i_adapter	All resolutions now work with t2i adapter for SDXL.	2 years ago
taesd	Add taesd and taesdxl to VAELoader node.	1 year ago
checkpoint_pickle.py	Remove pytorch_lightning dependency.	2 years ago
cli_args.py	UNET weights can now be stored in fp8.	1 year ago
clip_config_bigg.json	This is unused but it should be 1280.	2 years ago
clip_model.py	Cleaner CLIP text encoder implementation.	1 year ago
clip_vision.py	Faster clip image processing.	1 year ago
clip_vision_config_g.json	Add support for clip g vision model to CLIPVisionLoader.	2 years 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
conds.py	Add a CONDConstant for passing non tensor conds to unet.	1 year ago
controlnet.py	Fix control lora on fp8.	1 year ago
diffusers_convert.py	Fix diffusers VAE loading.	2 years ago
diffusers_load.py	Make VAE code closer to sgm.	1 year ago
gligen.py	Smarter memory management.	2 years ago
latent_formats.py	Supports TAESD models in safetensors format	1 year ago
lora.py	Add support for full diff lora keys.	1 year ago
model_base.py	UNET weights can now be stored in fp8.	1 year ago
model_detection.py	Fix importing diffusers unets.	1 year ago
model_management.py	Slightly faster lora applying.	1 year ago
model_patcher.py	Make deep shrink behave like it should.	1 year ago
model_sampling.py	.sigma and .timestep now return tensors on the same device as the input.	1 year ago
ops.py	All the unet ops with weights are now handled by comfy.ops	1 year ago
options.py	Only parse command line args when main.py is called.	1 year ago
sample.py	Fix memory issue with control loras.	1 year ago
samplers.py	Invert the start and end percentages in the code.	1 year ago
sd.py	Use smart model management for VAE to decrease latency.	1 year ago
sd1_clip.py	Cleaner CLIP text encoder implementation.	1 year ago
sd1_clip_config.json	Initial commit.	2 years ago
sd2_clip.py	Cleaner CLIP text encoder implementation.	1 year ago
sd2_clip_config.json	Move text_projection to base clip model.	2 years ago
sdxl_clip.py	Cleaner CLIP text encoder implementation.	1 year ago
supported_models.py	Support SD2.1 turbo checkpoint.	1 year ago
supported_models_base.py	Add sampling_settings so models can specify specific sampling settings.	1 year ago
utils.py	A different way of handling multiple images passed to SVD.	1 year ago