clarencechen 151998e1c2 Update final CPU offloading code for more diffusion pipelines (#5589) ...

* Update final model offload for more pipelines

Add test to ensure all pipeline components are returned to CPU after
execution with model offloading

* Add comment to explain early UNet offload in Text-to-Video pipeline

* Style

2023-11-01 21:22:56 +01:00

..

fixtures

[Release 0.21] Bump version (#5018)

2023-09-14 18:28:57 +02:00

lora

[PEFT] Fix scale unscale with LoRA adapters (#5417)

2023-10-21 22:17:18 +05:30

models

Added support to create asymmetrical U-Net structures (#5400)

2023-10-20 11:42:28 +02:00

others

Register BaseOutput subclasses as supported torch.utils._pytree nodes (#5459)

2023-10-24 15:01:47 +05:30

pipelines

Update final CPU offloading code for more diffusion pipelines (#5589)

2023-11-01 21:22:56 +01:00

schedulers

Stabilize DPM++, especially for SDXL and SDE-DPM++ (#5541)

2023-10-30 06:36:53 -10:00

__init__.py

fix issues with loading, add test for pipeline

2022-06-07 15:40:36 +02:00

conftest.py

[Copyright] 2023 (#2524)

2023-03-01 10:31:00 +01:00