comfyanonymous 88172a4339 Fix torch compile issue.		2025-12-04 23:58:29 -05:00
..
audio_encoders
cldm	Add better error message for common error. (#10846)	2025-11-23 04:55:22 -05:00
comfy_types
extra_samplers
image_encoders
k_diffusion
ldm	Implement temporal rolling VAE (Major VRAM reductions in Hunyuan and Kandinsky) (#10995)	2025-12-02 22:49:29 -05:00
sd1_tokenizer
t2i_adapter
taesd	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
text_encoders	Remove.	2025-12-04 19:17:06 -05:00
weight_adapter	Fix loras not working on mixed fp8. (#10899)	2025-11-26 00:07:58 -05:00
checkpoint_pickle.py
cli_args.py	feat: Support ComfyUI-Manager for pip version (#7555)	2025-12-01 22:32:52 -05:00
clip_config_bigg.json
clip_model.py
clip_vision_config_g.json
clip_vision_config_h.json
clip_vision_config_vitl_336_llava.json
clip_vision_config_vitl_336.json
clip_vision_config_vitl.json
clip_vision_siglip_384.json
clip_vision_siglip_512.json
clip_vision.py
conds.py
context_windows.py
controlnet.py
diffusers_convert.py
diffusers_load.py
float.py
gligen.py
hooks.py
latent_formats.py	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
lora_convert.py
lora.py	Add some missing z image lora layers. (#10980)	2025-11-28 23:55:00 -05:00
model_base.py	Remove unused json import	2025-12-03 19:43:40 -05:00
model_detection.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00
model_management.py	mm: wrap the raw stream in context manager (#10958)	2025-11-28 16:38:12 -05:00
model_patcher.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00
model_sampling.py
nested_tensor.py
ops.py	Fix torch compile issue.	2025-12-04 23:58:29 -05:00
options.py
patcher_extension.py
pixel_space_convert.py
quant_ops.py	torch compile fixes.	2025-12-04 22:17:13 -05:00
rmsnorm.py
sample.py
sampler_helpers.py
samplers.py
sd1_clip_config.json
sd1_clip.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00
sd.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00
sdxl_clip.py
supported_models_base.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00
supported_models.py	Hack to make zimage work in fp16. (#11057)	2025-12-02 17:11:58 -05:00
utils.py	Make old fp8 system use new mixed quant system.	2025-12-03 19:28:33 -05:00