Lincoln Stein dc134935c8 replace load_and_cache_model() with load_remote_model() and load_local_odel()

2024-06-07 14:12:16 +10:00

..

app

replace load_and_cache_model() with load_remote_model() and load_local_odel()

2024-06-07 14:12:16 +10:00

assets

feat(api): chore: pydantic & fastapi upgrade

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

backend

add support for generic loading of diffusers directories

2024-06-07 13:54:30 +10:00

configs

feat(mm): support sdxl ckpt inpainting models

2024-04-28 12:57:27 +10:00

frontend

feat(ui): add help icon to compare toolbar

2024-06-02 15:30:00 +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

2024-05-24 08:00:03 +10:00

__init__.py

…