InvokeAI/invokeai/backend/model_manager/load
Lincoln Stein a23dedd2ee make model manager v2 ready for PR review
- Replace legacy model manager service with the v2 manager.

- Update invocations to use new load interface.

- Fixed many but not all type checking errors in the invocations. Most
  were unrelated to model manager

- Updated routes. All the new routes live under the route tag
  `model_manager_v2`. To avoid confusion with the old routes,
  they have the URL prefix `/api/v2/models`. The old routes
  have been de-registered.

- Added a pytest for the loader.

- Updated documentation in contributing/MODEL_MANAGER.md
2024-03-01 10:42:33 +11:00
..
convert_cache loaders for main, controlnet, ip-adapter, clipvision and t2i 2024-03-01 10:42:33 +11:00
model_cache make model manager v2 ready for PR review 2024-03-01 10:42:33 +11:00
model_loaders make model manager v2 ready for PR review 2024-03-01 10:42:33 +11:00
__init__.py consolidate model manager parts into a single class 2024-03-01 10:42:33 +11:00
load_base.py make model manager v2 ready for PR review 2024-03-01 10:42:33 +11:00
load_default.py make model manager v2 ready for PR review 2024-03-01 10:42:33 +11:00
memory_snapshot.py added textual inversion and lora loaders 2024-03-01 10:42:33 +11:00
model_util.py make model manager v2 ready for PR review 2024-03-01 10:42:33 +11:00
optimizations.py add ram cache module and support files 2024-03-01 10:42:33 +11:00