ComfyUI/comfy
comfyanonymous 045377ea89 Add a --reserve-vram argument if you don't want comfy to use all of it.
--reserve-vram 1.0 for example will make ComfyUI try to keep 1GB vram free.

This can also be useful if workflows are failing because of OOM errors but
in that case please report it if --reserve-vram improves your situation.
2024-08-19 17:16:18 -04:00
..
cldm
extra_samplers
k_diffusion Automatically use RF variant of dpmpp_2s_ancestral if RF model. 2024-08-18 00:47:25 -04:00
ldm Indentation. 2024-08-17 23:00:44 -04:00
sd1_tokenizer
t2i_adapter
taesd
text_encoders Add model_options for text encoder. 2024-08-17 11:17:20 -04:00
checkpoint_pickle.py
cli_args.py Add a --reserve-vram argument if you don't want comfy to use all of it. 2024-08-19 17:16:18 -04:00
clip_config_bigg.json
clip_model.py
clip_vision.py
clip_vision_config_g.json
clip_vision_config_h.json
clip_vision_config_vitl.json
clip_vision_config_vitl_336.json
conds.py
controlnet.py
diffusers_convert.py
diffusers_load.py
float.py Better subnormal fp8 stochastic rounding. Thanks Ashen. 2024-08-19 13:38:03 -04:00
gligen.py
latent_formats.py
lora.py
model_base.py
model_detection.py
model_management.py Add a --reserve-vram argument if you don't want comfy to use all of it. 2024-08-19 17:16:18 -04:00
model_patcher.py Bug fixes. 2024-08-19 16:28:55 -04:00
model_sampling.py
ops.py Less broken non blocking? 2024-08-18 16:53:17 -04:00
options.py
sample.py
sampler_helpers.py
samplers.py Automatically use RF variant of dpmpp_2s_ancestral if RF model. 2024-08-18 00:47:25 -04:00
sd.py unet -> diffusion_models. 2024-08-17 21:31:04 -04:00
sd1_clip.py Add model_options for text encoder. 2024-08-17 11:17:20 -04:00
sd1_clip_config.json
sdxl_clip.py Add model_options for text encoder. 2024-08-17 11:17:20 -04:00
supported_models.py
supported_models_base.py
types.py
utils.py