comfyanonymous 824e4935f5 Add dtype parameter to VAE object.		2023-12-12 12:03:29 -05:00
..
cldm	Add manual cast to controlnet.	2023-12-12 11:32:42 -05:00
extra_samplers	…
k_diffusion	…
ldm	Refactor comfy.ops	2023-12-11 23:27:13 -05:00
sd1_tokenizer	…
t2i_adapter	…
taesd	…
checkpoint_pickle.py	…
cli_args.py	Add an option --fp16-unet to force using fp16 for the unet.	2023-12-11 18:36:29 -05:00
clip_config_bigg.json	…
clip_model.py	Use own clip vision model implementation.	2023-12-09 11:56:31 -05:00
clip_vision.py	Refactor comfy.ops	2023-12-11 23:27:13 -05:00
clip_vision_config_g.json	…
clip_vision_config_h.json	…
clip_vision_config_vitl.json	…
conds.py	…
controlnet.py	Add manual cast to controlnet.	2023-12-12 11:32:42 -05:00
diffusers_convert.py	…
diffusers_load.py	…
gligen.py	…
latent_formats.py	…
lora.py	Implement GLora.	2023-12-09 18:15:26 -05:00
model_base.py	Use inference dtype for unet memory usage estimation.	2023-12-11 23:50:38 -05:00
model_detection.py	…
model_management.py	Add an option --fp16-unet to force using fp16 for the unet.	2023-12-11 18:36:29 -05:00
model_patcher.py	Implement GLora.	2023-12-09 18:15:26 -05:00
model_sampling.py	Add linear_start and linear_end to model_config.sampling_settings	2023-12-08 02:49:30 -05:00
ops.py	Refactor comfy.ops	2023-12-11 23:27:13 -05:00
options.py	…
sample.py	Make --gpu-only put intermediate values in GPU memory instead of cpu.	2023-12-08 02:35:45 -05:00
samplers.py	Cleanup.	2023-12-08 16:02:08 -05:00
sd.py	Add dtype parameter to VAE object.	2023-12-12 12:03:29 -05:00
sd1_clip.py	Switch text encoder to manual cast.	2023-12-10 23:00:54 -05:00
sd1_clip_config.json	…
sd2_clip.py	…
sd2_clip_config.json	…
sdxl_clip.py	…
supported_models.py	…
supported_models_base.py	Use faster manual cast for fp8 in unet.	2023-12-11 18:24:44 -05:00
utils.py	Make --gpu-only put intermediate values in GPU memory instead of cpu.	2023-12-08 02:35:45 -05:00