InvokeAI/invokeai
psychedelicious 5127fd6320 fix(ui): control adapter autoprocess jank
If you change the control model and the new model has the same default processor, we would still re-process the image, even if there was no need to do so.

With this change, if the image and processor config are unchanged, we bail out.
2024-05-19 07:25:48 +10:00
..
app chore(app): ruff 2024-05-18 09:21:45 +10:00
assets feat(api): chore: pydantic & fastapi upgrade 2023-10-17 14:59:25 +11:00
backend feat(nodes): use new blur_if_nsfw method 2024-05-14 07:23:38 +10:00
configs feat(mm): support sdxl ckpt inpainting models 2024-04-28 12:57:27 +10:00
frontend fix(ui): control adapter autoprocess jank 2024-05-19 07:25:48 +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 2024-05-14 07:37:02 +10:00
__init__.py