Lincoln Stein 7c39929758 support VRAM caching of dict models that lack to()

2024-04-28 13:41:06 -04:00

..

app

support VRAM caching of dict models that lack to()

2024-04-28 13:41:06 -04:00

assets

feat(api): chore: pydantic & fastapi upgrade

2023-10-17 14:59:25 +11:00

backend

support VRAM caching of dict models that lack to()

2024-04-28 13:41:06 -04:00

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