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 a252963f95 --disable-smart-memory now unloads everything like it did originally.		1 year ago
..
cldm	Add manual cast to controlnet.	1 year ago
extra_samplers	Remove useless argument from uni_pc sampler.	1 year ago
k_diffusion	heunpp2 sampler.	1 year ago
ldm	A few missing comfy ops in the VAE.	1 year ago
sd1_tokenizer	…
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	…
cli_args.py	Add --deterministic option to make pytorch use deterministic algorithms.	1 year ago
clip_config_bigg.json	…
clip_model.py	Use own clip vision model implementation.	1 year ago
clip_vision.py	Don't resize clip vision image when the size is already good.	1 year ago
clip_vision_config_g.json	…
clip_vision_config_h.json	…
clip_vision_config_vitl.json	…
conds.py	Add a CONDConstant for passing non tensor conds to unet.	1 year ago
controlnet.py	Greatly improve lowvram sampling speed by getting rid of accelerate.	1 year ago
diffusers_convert.py	…
diffusers_load.py	Make VAE code closer to sgm.	1 year ago
gligen.py	…
latent_formats.py	Supports TAESD models in safetensors format	1 year ago
lora.py	Implement GLora.	1 year ago
model_base.py	Greatly improve lowvram sampling speed by getting rid of accelerate.	1 year ago
model_detection.py	Support segmind vega model.	1 year ago
model_management.py	--disable-smart-memory now unloads everything like it did originally.	1 year ago
model_patcher.py	Fix SAG not working with cfg 1.0	1 year ago
model_sampling.py	Add linear_start and linear_end to model_config.sampling_settings	1 year ago
ops.py	Greatly improve lowvram sampling speed by getting rid of accelerate.	1 year ago
options.py	Only parse command line args when main.py is called.	1 year ago
sample.py	Support stable zero 123 model.	1 year ago
samplers.py	Fix regression with inpaint model.	1 year ago
sd.py	Add dtype parameter to VAE object.	1 year ago
sd1_clip.py	Switch text encoder to manual cast.	1 year ago
sd1_clip_config.json	…
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 stable zero 123 model.	1 year ago
supported_models_base.py	Use faster manual cast for fp8 in unet.	1 year ago
utils.py	Make --gpu-only put intermediate values in GPU memory instead of cpu.	1 year ago