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> |
||
|---|---|---|
| .. | ||
| convert_cache | ||
| model_cache | ||
| model_loaders | ||
| __init__.py | ||
| load_base.py | ||
| load_default.py | ||
| memory_snapshot.py | ||
| model_loader_registry.py | ||
| model_util.py | ||
| optimizations.py | ||