InvokeAI/invokeai/app
Lincoln Stein 49df4fa120 BREAKING CHANGES: invocations now require model key, not base/type/name
- Implement new model loader and modify invocations and embeddings

- Finish implementation loaders for all models currently supported by
  InvokeAI.

- Move lora, textual_inversion, and model patching support into
  backend/embeddings.

- Restore support for model cache statistics collection (a little ugly,
  needs work).

- Fixed up invocations that load and patch models.

- Move seamless and silencewarnings utils into better location
2024-02-29 13:16:37 -05:00
..
api BREAKING CHANGES: invocations now require model key, not base/type/name 2024-02-29 13:16:37 -05:00
assets/images tweaks in response to psychedelicious review of PR 2023-07-26 15:27:04 +10:00
invocations BREAKING CHANGES: invocations now require model key, not base/type/name 2024-02-29 13:16:37 -05:00
services BREAKING CHANGES: invocations now require model key, not base/type/name 2024-02-29 13:16:37 -05:00
shared tidy(nodes): move all field things to fields.py 2024-02-29 13:16:35 -05:00
util feat(nodes): update all invocations to use new invocation context 2024-02-29 13:16:35 -05:00
api_app.py tidy(nodes): move all field things to fields.py 2024-02-29 13:16:35 -05:00