mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
c87497fd54
- Move base of t2i and clip_vision config models to DiffusersBase, which contains a field to record the model variant (e.g. "fp16") - This restore the ability to load fp16 t2i and clip_vision models - Also add defensive coding to load the vanilla model when the fp16 model has been replaced (or more likely, user's preferences changed since installation) Co-authored-by: Lincoln Stein <lstein@gmail.com> |
||
|---|---|---|
| .. | ||
| embeddings | ||
| image_util | ||
| install | ||
| ip_adapter | ||
| model_hash | ||
| model_manager | ||
| onnx | ||
| stable_diffusion | ||
| tiles | ||
| training | ||
| util | ||
| __init__.py | ||
| lora.py | ||
| model_patcher.py | ||
| raw_model.py | ||
| textual_inversion.py | ||