Jonathan 9eed1919c2 Strategize slicing based on free [V]RAM (#2572) ...

Strategize slicing based on free [V]RAM when not using xformers. Free [V]RAM is evaluated at every generation. When there's enough memory, the entire generation occurs without slicing. If there is not enough free memory, we use diffusers' sliced attention.

2023-02-12 18:24:15 +00:00

..

__init__.py

rename all modules from ldm.dream to ldm.invoke

2022-10-08 11:37:23 -04:00

base.py

Refactor CUDA cache clearing to add statistical reporting. (#2553)

2023-02-06 12:53:30 -05:00

diffusers_pipeline.py

Strategize slicing based on free [V]RAM (#2572)

2023-02-12 18:24:15 +00:00

embiggen.py

use 🧨diffusers model (#1583)

2023-01-15 09:22:46 -05:00

img2img.py

fix crash in txt2img and img2img w/ inpainting models and perlin > 0

2023-02-05 22:55:08 -05:00

inpaint.py

fix crash when text mask applied to img2img (#2526)

2023-02-05 15:26:40 +00:00

omnibus.py

use 🧨diffusers model (#1583)

2023-01-15 09:22:46 -05:00

txt2img2img.py

Refactor CUDA cache clearing to add statistical reporting. (#2553)

2023-02-06 12:53:30 -05:00

txt2img.py

fix crash in txt2img and img2img w/ inpainting models and perlin > 0

2023-02-05 22:55:08 -05:00