Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
8bf9fd34ad
InvokeAI/invokeai/app/services/invocation_cache
History
psychedelicious 0710fb3fb0 feat(nodes): replace latents service with tensors and conditioning services 
- New generic class `PickleStorageBase`, implements the same API as `LatentsStorageBase`, use for storing non-serializable data via pickling
- Implementation `PickleStorageTorch` uses `torch.save` and `torch.load`, same as `LatentsStorageDisk`
- Add `tensors: PickleStorageBase[torch.Tensor]` to `InvocationServices`
- Add `conditioning: PickleStorageBase[ConditioningFieldData]` to `InvocationServices`
- Remove `latents` service and all `LatentsStorage` classes
- Update `InvocationContext` and all usage of old `latents` service to use the new services/context wrapper methods
2024-03-01 10:42:33 +11:00
..
__init__.py feat: queued generation (#4502) 2023-09-20 15:09:24 +10:00
invocation_cache_base.py feat(nodes): add enable, disable, status to invocation cache 2023-09-21 09:45:52 -04:00
invocation_cache_common.py feat(nodes): add enable, disable, status to invocation cache 2023-09-21 09:45:52 -04:00
invocation_cache_memory.py feat(nodes): replace latents service with tensors and conditioning services 2024-03-01 10:42:33 +11:00