Gæros 298ce67999 [LoRA] text encoder: read the ranks for all the attn modules (#8324) ...

* [LoRA] text encoder: read the ranks for all the attn modules

 * In addition to out_proj, read the ranks of adapters for q_proj, k_proj, and  v_proj

 * Allow missing adapters (UNet already supports this)

* ruff format loaders.lora

* [LoRA] add tests for partial text encoders LoRAs

* [LoRA] update test_simple_inference_with_partial_text_lora to be deterministic

* [LoRA] comment justifying test_simple_inference_with_partial_text_lora

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

2024-06-18 21:10:50 +01:00

..

fixtures

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00

lora

[LoRA] text encoder: read the ranks for all the attn modules (#8324)

2024-06-18 21:10:50 +01:00

models

Fix sharding when no device_map is passed (#8531)

2024-06-18 05:47:23 -10:00

others

#7535 Update FloatTensor type hints to Tensor (#7883)

2024-05-10 09:53:31 -10:00

pipelines

remove the deprecated prepare_mask_and_masked_image function (#8512)

2024-06-13 14:59:21 +01:00

schedulers

[scheduler] support custom timesteps and sigmas (#7817)

2024-05-09 11:07:43 -10:00

single_file

[tests] decorate StableDiffusion21PipelineSingleFileSlowTests with slow. (#7941)

2024-05-14 14:26:21 -10:00

__init__.py

fix issues with loading, add test for pipeline

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

conftest.py

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00