mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
d0a71dc361
Code cleanup and attention.py einsum_ops update for M1 16-32GB performance. Expected: On par with fastest ever from 8 to 128GB for 512x512. Allows large images. |
||
---|---|---|
.. | ||
diffusionmodules | ||
distributions | ||
encoders | ||
image_degradation | ||
losses | ||
attention.py | ||
ema.py | ||
embedding_manager.py | ||
x_transformer.py |