InvokeAI/invokeai
psychedelicious 241a1fdb57 feat(mm): support sdxl ckpt inpainting models
There are only a couple SDXL inpainting models, and my tests indicate they are not as good as SD1.5 inpainting, but at least we support them now.

- Add the config file. This matches what is used in A1111. The only difference from the non-inpainting SDXL config is the number of in-channels.
- Update the legacy config maps to use this config file.
2024-04-28 12:57:27 +10:00
..
app tidy(backend): clean up controlnet_utils 2024-04-25 13:20:09 +10:00
assets feat(api): chore: pydantic & fastapi upgrade 2023-10-17 14:59:25 +11:00
backend feat(mm): support sdxl ckpt inpainting models 2024-04-28 12:57:27 +10:00
configs feat(mm): support sdxl ckpt inpainting models 2024-04-28 12:57:27 +10:00
frontend chore(ui): lint 2024-04-24 20:09:52 +10:00
invocation_api Remove support for Prompt-to-Prompt cross-attention control (aka .swap()). This feature is not widely used. It does not work with SDXL and is incompatible with IP-Adapter and regional prompting. The implementation is also intertwined with both text embedding and the UNet attention layers, resulting in a high maintenance burden. For all of these reasons, we have decided to drop support. 2024-04-09 10:57:02 -04:00
version Update invokeai_version.py 2024-04-25 12:31:59 +10:00
__init__.py Various fixes 2023-01-30 18:42:17 -05:00