mirror of
https://github.com/invoke-ai/InvokeAI
synced 2026-05-02 11:42:09 +02:00
1. only load triton on linux machines 2. require pip >= 23.0 so that editable installs can run without setup.py 3. model files default to SD-1.5, not 2.1 4. use diffusers model of inpainting rather than ckpt 5. selected a new set of initial models based on # of likes at huggingface |
||
|---|---|---|
| .. | ||
| assets | ||
| backend | ||
| configs | ||
| frontend | ||
| __init__.py | ||
| README | ||
After version 2.3 is released, the ldm/invoke modules will be migrated to this location so that we have a proper invokeai distribution. Currently it is only being used for data files.