William a3b9b3c1c3 Memory check before inference to avoid VAE Decode using exceeded VRAM. ...

Check if free memory is not less than expected before doing actual decoding,
and if it fails, switch to tiled VAE decoding directly.

It seems PyTorch may continue occupying memory until the model is destroyed
after OOM occurs. This commit tries to avoid OOM from happening in the first
place for VAE Decode.

This is for VAE Decode ran with exceeded VRAM from #5737.

2024-11-24 18:47:01 +08:00

..

cldm

Support AliMama SD3 and Flux inpaint controlnets.

2024-09-14 09:05:16 -04:00

extra_samplers

Avoid SyntaxWarning in UniPC docstring (#5442)

2024-10-31 15:17:26 -04:00

k_diffusion

Make euler_ancestral work on flow models (credit: Ashen).

2024-10-25 19:53:44 -04:00

ldm

Skip layer guidance node now works on LTX-Video.

2024-11-23 10:33:05 -05:00

sd1_tokenizer

Initial commit.

2023-01-16 22:37:14 -05:00

t2i_adapter

Controlnet refactor.

2024-06-27 18:43:11 -04:00

taesd

Improvements to the TAESD3 implementation.

2024-06-16 02:04:24 -04:00

text_encoders

Support Lightricks LTX-Video model.

2024-11-22 08:46:39 -05:00

checkpoint_pickle.py

Remove pytorch_lightning dependency.

2023-06-13 10:11:33 -04:00

cli_args.py

Let --verbose have an argument for the log level.

2024-10-04 10:05:34 -04:00

clip_config_bigg.json

Fix potential issue with non clip text embeddings.

2024-07-30 14:41:13 -04:00

clip_model.py

Support new flux model variants.

2024-11-21 08:38:23 -05:00

clip_vision_config_g.json

Add support for clip g vision model to CLIPVisionLoader.

2023-08-18 11:13:29 -04:00

clip_vision_config_h.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision_config_vitl_336.json

support clip-vit-large-patch14-336 (#4042)

2024-07-17 13:12:50 -04:00

clip_vision_config_vitl.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision_siglip_384.json

Support new flux model variants.

2024-11-21 08:38:23 -05:00

clip_vision.py

Support new flux model variants.

2024-11-21 08:38:23 -05:00

comfy_types.py

types -> comfy_types to fix import issue.

2024-09-12 03:57:46 -04:00

conds.py

Fix bug with cosxl edit model.

2024-06-10 16:00:03 -04:00

controlnet.py

Fix ControlLora issue with last commit.

2024-10-23 17:02:40 -04:00

diffusers_convert.py

Fix saving text encoder in fp8.

2024-04-02 11:46:34 -04:00

diffusers_load.py

load_unet -> load_diffusion_model with a model_options argument.

2024-08-12 23:20:57 -04:00

float.py

Clamp output when rounding weight to prevent Nan.

2024-10-19 19:07:10 -04:00

gligen.py

Fix gligen lowvram mode.

2024-02-18 02:20:23 -05:00

latent_formats.py

Support Lightricks LTX-Video model.

2024-11-22 08:46:39 -05:00

lora_convert.py

Support new flux model variants.

2024-11-21 08:38:23 -05:00

lora.py

Add some new weight patching functionality.

2024-11-21 07:19:17 -05:00

model_base.py

Remove print.

2024-11-22 10:49:15 -05:00

model_detection.py

Support Lightricks LTX-Video model.

2024-11-22 08:46:39 -05:00

model_management.py

Bump up mac version for attention upcast bug workaround.

2024-10-31 15:15:31 -04:00

model_patcher.py

Some improvements to the lowvram unloading.

2024-11-22 20:59:15 -05:00

model_sampling.py

Refactor so that zsnr can be set in the sampling_settings.

2024-11-11 04:55:56 -05:00

ops.py

Fix lowvram edge case.

2024-10-22 16:34:50 -04:00

options.py

Only parse command line args when main.py is called.

2023-09-13 11:38:20 -04:00

sample.py

Reshape the empty latent image to the right amount of channels if needed.

2024-06-08 02:35:08 -04:00

sampler_helpers.py

Properly handle and reshape masks when used on 3d latents.

2024-11-09 15:30:19 -05:00

samplers.py

Basic Genmo Mochi video model support.

2024-10-26 06:54:00 -04:00

sd1_clip_config.json

Fix potential issue with non clip text embeddings.

2024-07-30 14:41:13 -04:00

sd1_clip.py

Support scaled fp8 t5xxl model.

2024-10-20 22:27:00 -04:00

sd.py

Memory check before inference to avoid VAE Decode using exceeded VRAM.

2024-11-24 18:47:01 +08:00

sdxl_clip.py

Long CLIP L support for SDXL, SD3 and Flux.

2024-09-15 07:59:38 -04:00

supported_models_base.py

Mixed precision diffusion models with scaled fp8.

2024-10-21 18:12:51 -04:00

supported_models.py

Support Lightricks LTX-Video model.

2024-11-22 08:46:39 -05:00

utils.py

Fix issue with 3d masks.

2024-11-13 07:18:30 -05:00