mirror of
https://github.com/invoke-ai/InvokeAI
synced 2026-03-29 19:15:01 +02:00
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.
|
||
|---|---|---|
| .. | ||
| diffusionmodules | ||
| distributions | ||
| encoders | ||
| image_degradation | ||
| losses | ||
| attention.py | ||
| ema.py | ||
| embedding_manager.py | ||
| x_transformer.py | ||