- Implement new model loader and modify invocations and embeddings
- Finish implementation loaders for all models currently supported by
InvokeAI.
- Move lora, textual_inversion, and model patching support into
backend/embeddings.
- Restore support for model cache statistics collection (a little ugly,
needs work).
- Fixed up invocations that load and patch models.
- Move seamless and silencewarnings utils into better location
- Cache stat collection enabled.
- Implemented ONNX loading.
- Add ability to specify the repo version variant in installer CLI.
- If caller asks for a repo version that doesn't exist, will fall back
to empty version rather than raising an error.
We have two different classes named `ModelInfo` which might need to be used by API consumers. We need to export both but have to deal with this naming collision.
The `ModelInfo` I've renamed here is the one that is returned when a model is loaded. It's the object least likely to be used by API consumers.
* feat: allow bfloat16 to be configurable in invoke.yaml
* fix: `torch_dtype()` util
- Use `choose_precision` to get the precision string
- Do not reference deprecated `config.full_precision` flat (why does this still exist?), if a user had this enabled it would override their actual precision setting and potentially cause a lot of confusion.
---------
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
* remove MacOS Sonoma check in devices.py
As of pytorch 2.1.0, float16 works with our MPS fixes on Sonoma, so the check is no longer needed.
* remove unused platform import
Do not use `strict=True` when scaling controlnet conditioning.
When using `guess_mode` (e.g. `more_control` or `more_prompt`), `down_block_res_samples` and `scales` are zipped.
These two objects are of different lengths, so using zip's strict mode raises an error.
In testing, `len(scales) === len(down_block_res_samples) + 1`.
It appears this behaviour is intentional, as the final "extra" item in `scales` is used immediately afterwards.
