psychedelicious a18d7adad4 fix(ui): allow image dims multiple of 32 with SDXL and T2I adapter ...

See https://github.com/invoke-ai/InvokeAI/pull/6342#issuecomment-2109912452 for discussion.

2024-05-17 23:38:54 +10:00

..

app

feat(nodes): add LoRASelectorInvocation, LoRACollectionLoader, SDXLLoRACollectionLoader

2024-05-15 14:09:44 +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): allow image dims multiple of 32 with SDXL and T2I adapter

2024-05-17 23:38:54 +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

…