You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
comfyanonymous 3fd87cbd21 Slightly smarter batching behaviour.
Try to keep batch sizes more consistent which seems to improve things on
AMD GPUs.
2 years ago
..
k_diffusion Add some low vram modes: --lowvram and --novram 2 years ago
ldm Lower the chances of an OOM. 2 years ago
sd1_tokenizer
model_management.py Remove print. 2 years ago
samplers.py Slightly smarter batching behaviour. 2 years ago
sd.py Don't unload/reload model from CPU uselessly. 2 years ago
sd1_clip.py Add support for textual inversion embedding for SD1.x CLIP. 2 years ago
sd1_clip_config.json
sd2_clip.py Embeddings/textual inversion support for SD2.x 2 years ago
sd2_clip_config.json Use transformers CLIP instead of open_clip for SD2.x 2 years ago