comfyanonymous 87b00b37f6 Added an experimental VAEDecodeTiled. ...

This decodes the image with the VAE in tiles which should be faster and
use less vram.

It's in the _for_testing section so I might change/remove it or even
add the functionality to the regular VAEDecode node depending on how
well it performs which means don't depend too much on it.

2023-02-24 02:10:10 -05:00

..

cldm

Add ControlNet support.

2023-02-16 10:38:08 -05:00

extra_samplers

Uni_PC: make max denoise behave more like other samplers.

2023-02-22 02:21:06 -05:00

k_diffusion

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

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

ldm

Implement DDIM sampler.

2023-02-22 21:10:19 -05:00

sd1_tokenizer

Initial commit.

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

model_management.py

Add: --highvram for when you want models to stay on the vram.

2023-02-17 21:27:02 -05:00

samplers.py

Implement DDIM sampler.

2023-02-22 21:10:19 -05:00

sd1_clip_config.json

Initial commit.

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

sd1_clip.py

Support old pytorch.

2023-02-19 16:59:03 -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

Added an experimental VAEDecodeTiled.

2023-02-24 02:10:10 -05:00

utils.py

Add ControlNet support.

2023-02-16 10:38:08 -05:00