mirror of
https://github.com/invoke-ai/InvokeAI
synced 2026-03-16 11:50:19 +01:00
Fixes:
File "stable-diffusion/ldm/modules/diffusionmodules/model.py", line 37, in nonlinearity
return x*torch.sigmoid(x)
RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB [..]
Now up to 1536x1280 is possible on 8GB VRAM.
Also remove unused SiLU class.
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| model.py | ||
| openaimodel.py | ||
| util.py | ||