comfyanonymous 3fd87cbd21 Slightly smarter batching behaviour. ...

Try to keep batch sizes more consistent which seems to improve things on
AMD GPUs.

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

..

k_diffusion

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

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

ldm

Lower the chances of an OOM.

2023-02-08 14:24:27 -05:00

sd1_tokenizer

Initial commit.

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

model_management.py

Remove print.

2023-02-08 14:51:18 -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

Add support for textual inversion embedding for SD1.x CLIP.

2023-01-29 18:46:44 -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