comfyanonymous 509c7dfc6d Use real softmax in split op to fix issue with some images.

2023-02-10 03:13:49 -05:00

..

k_diffusion

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

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

ldm

Use real softmax in split op to fix issue with some images.

2023-02-10 03:13:49 -05:00

sd1_tokenizer

Initial commit.

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

model_management.py

Automatically enable lowvram mode if vram is less than 4GB.

2023-02-10 00:47:56 -05:00

samplers.py

Slightly smarter batching behaviour.

2023-02-08 17:28:43 -05:00

sd1_clip_config.json

Initial commit.

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

sd1_clip.py

Fix embedding not working when on new line.

2023-02-09 14:12:02 -05:00

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

Embeddings/textual inversion support for SD2.x

2023-02-05 15:49:03 -05:00

sd.py

Don't unload/reload model from CPU uselessly.

2023-02-08 03:40:43 -05:00