InvokeAI/invokeai/backend/model_manager/load/model_loaders
Lincoln Stein 3e0fb45dd7
Load single-file checkpoints directly without conversion (#6510)
* use model_class.load_singlefile() instead of converting; works, but performance is poor

* adjust the convert api - not right just yet

* working, needs sql migrator update

* rename migration_11 before conflict merge with main

* Update invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* Update invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* implement lightweight version-by-version config migration

* simplified config schema migration code

* associate sdxl config with sdxl VAEs

* remove use of original_config_file in load_single_file()

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
2024-06-27 17:31:28 -04:00
..
__init__.py model loading and conversion implemented for vaes 2024-03-01 10:42:33 +11:00
controlnet.py Load single-file checkpoints directly without conversion (#6510) 2024-06-27 17:31:28 -04:00
generic_diffusers.py add support for generic loading of diffusers directories 2024-06-07 13:54:30 +10:00
ip_adapter.py chore: clean up merge conflicts 2024-04-03 20:28:00 +05:30
lora.py Load single-file checkpoints directly without conversion (#6510) 2024-06-27 17:31:28 -04:00
onnx.py [mm] Do not write diffuser model to disk when convert_cache set to zero (#6072) 2024-03-29 16:11:08 -04:00
stable_diffusion.py Load single-file checkpoints directly without conversion (#6510) 2024-06-27 17:31:28 -04:00
textual_inversion.py [mm] Do not write diffuser model to disk when convert_cache set to zero (#6072) 2024-03-29 16:11:08 -04:00
vae.py Load single-file checkpoints directly without conversion (#6510) 2024-06-27 17:31:28 -04:00