mirror of
https://github.com/invoke-ai/InvokeAI
synced 2026-04-28 01:32:24 +02:00
1. If tensors are passed to inpaint as init_image and/or init_mask, then the post-generation image fixup code will be skipped. 2. Post-generation image fixup will work with either a black and white "L" or "RGB" mask, or an "RGBA" mask. |
||
|---|---|---|
| .. | ||
| autoencoder | ||
| latent-diffusion | ||
| retrieval-augmented-diffusion | ||
| stable-diffusion | ||
| models.yaml | ||