comfyanonymous 6fc4917634 Make maximum_batch_area take into account python2.0 attention function. ...

More conservative xformers maximum_batch_area.

2023-05-06 19:58:54 -04:00

..

cldm

Fix imports.

2023-05-04 18:10:29 -04:00

extra_samplers

Add a total_steps value to sampler callback.

2023-05-03 12:58:10 -04:00

k_diffusion

Add some low vram modes: --lowvram and --novram

2023-02-08 11:37:10 -05:00

ldm

Lowvram mode for gligen and fix some lowvram issues.

2023-05-05 18:11:41 -04:00

sd1_tokenizer

Initial commit.

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

t2i_adapter

Update T2I adapter code to latest.

2023-03-03 18:46:49 -05:00

cli_args.py

You can now select the device index with: --directml id

2023-04-28 16:51:35 -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.json

Add support for unCLIP SD2.x models.

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

clip_vision.py

Fix for new transformers version.

2023-04-09 15:55:21 -04:00

diffusers_convert.py

Cleanup.

2023-04-07 02:31:46 -04:00

gligen.py

Lowvram mode for gligen and fix some lowvram issues.

2023-05-05 18:11:41 -04:00

model_management.py

Make maximum_batch_area take into account python2.0 attention function.

2023-05-06 19:58:54 -04:00

sample.py

Properly disable all progress bars when disable_pbar=True

2023-05-01 15:52:17 -04:00

samplers.py

Add a total_steps value to sampler callback.

2023-05-03 12:58:10 -04:00

sd1_clip_config.json

Initial commit.

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

sd1_clip.py

Search recursively in subfolders for embeddings.

2023-05-05 01:28:48 -04:00

sd2_clip_config.json

Use transformers CLIP instead of open_clip for SD2.x

2023-02-05 14:36:28 -05:00

sd2_clip.py

Some refactoring: from_tokens -> encode_from_tokens

2023-04-15 18:46:58 -04:00

sd.py

Fix imports.

2023-05-04 18:10:29 -04:00

utils.py

Refactor.

2023-05-03 17:48:35 -04:00