InvokeAI/invokeai
psychedelicious 385e93443a feat(ui): rp hotkeys
- Shift+C: Reset selected layer mask (same as canvas)
- Shift+D: Delete selected layer (cannot be Del, that deletes an image in gallery)
- Shift+A: Add layer (cannot be Ctrl+Shift+N, that opens a new window)
- Ctrl/Cmd+Wheel: Brush size (same as canvas)
2024-04-23 12:11:47 +10:00
..
app feat(nodes): image mask to tensor invocation 2024-04-20 11:32:08 -04:00
assets feat(api): chore: pydantic & fastapi upgrade 2023-10-17 14:59:25 +11:00
backend Re-enable app shutdown actions (#6244) 2024-04-19 06:45:42 -04:00
configs fix(mm): add missing v2-midas-inference.yaml 2024-03-27 07:48:54 -04:00
frontend feat(ui): rp hotkeys 2024-04-23 12:11:47 +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 Make it alpha 2024-04-22 10:54:21 -04:00
__init__.py Various fixes 2023-01-30 18:42:17 -05:00