- 25 Jul, 2024 2 commits
-
-
-
Sayak Paul authored
* introduce to promote reusability. * up * add more tests * up * remove comments. * fix fuse_nan test * clarify the scope of fuse_lora and unfuse_lora * remove space * rewrite fuse_lora a bit. * feedback * copy over load_lora_into_text_encoder. * address dhruv's feedback. * fix-copies * fix issubclass. * num_fused_loras * fix * fix * remove mapping * up * fix * style * fix-copies * change to SD3TransformerLoRALoadersMixin * Apply suggestions from code review Co-authored-by:
Dhruv Nair <dhruv.nair@gmail.com> * up * handle wuerstchen * up * move lora to lora_pipeline.py * up * fix-copies * fix documentation. * comment set_adapters(). * fix-copies * fix set_adapters() at the model level. * fix? * fix --------- Co-authored-by:
-
- 18 Jul, 2024 1 commit
-
-
Sayak Paul authored
* remove resume_download * fix: _fetch_index_file call. * remove resume_download from docs.
-
- 12 Jul, 2024 1 commit
-
-
Dhruv Nair authored
* update * update * update * update
-
- 05 Jul, 2024 1 commit
-
-
Dhruv Nair authored
* update * update * update * update
-
- 03 Jul, 2024 2 commits
-
-
Sayak Paul authored
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670)" This reverts commit a2071a18.
-
Sayak Paul authored
* introduce to promote reusability. * up * add more tests * up * remove comments. * fix fuse_nan test * clarify the scope of fuse_lora and unfuse_lora * remove space
-
- 01 Jul, 2024 1 commit
-
-
Dhruv Nair authored
update
-
- 28 Jun, 2024 1 commit
-
-
Luo Chaofan authored
* fix: ValueError when using FromOriginalModelMixin in subclasses #8440 (cherry picked from commit 92859978436acf844760fc0e992165b489d0180a) * Update src/diffusers/loaders/single_file_model.py Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
- 27 Jun, 2024 1 commit
-
-
Sayak Paul authored
fix conversion utility so that lora dora loads correctly
-
- 26 Jun, 2024 2 commits
-
-
Sayak Paul authored
fix vanilla fine-tuned lora loading.
-
Donald.Lee authored
* fix: unet save_attn_procs at custom diffusion * style: recover unchanaged parts(max line length 119) / mod: add condition * style: recover unchanaged parts(max line length 119) --------- Co-authored-by:
-
- 25 Jun, 2024 2 commits
-
-
YiYi Xu authored
* first draft --------- Co-authored-by:
yiyixuxu <yixu310@gmail,com> Co-authored-by:
Junhwa Song <ethan9867@gmail.com> Co-authored-by:
Ahn Donghoon (안동훈 / suno) <suno.vivid@gmail.com> Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com>
-
Linoy Tsaban authored
* add clip text-encoder training * no dora * text encoder traing fixes * text encoder traing fixes * text encoder training fixes * text encoder training fixes * text encoder training fixes * text encoder training fixes * add text_encoder layers to save_lora * style * fix imports * style * fix text encoder * review changes * review changes * review changes * minor change * add lora tag * style * add readme notes * add tests for clip encoders * style * typo * fixes * style * Update tests/lora/test_lora_layers_sd3.py Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
-
- 22 Jun, 2024 1 commit
-
-
Sayak Paul authored
* refactor lora conversion utility. * remove error raises. * add onetrainer support too.
-
- 21 Jun, 2024 1 commit
-
-
Álvaro Somoza authored
* fix * add check * key present is checked before * test case draft * aply suggestions * changed testing repo, back to old class * forgot docstring --------- Co-authored-by:
-
- 20 Jun, 2024 1 commit
-
-
Sayak Paul authored
* add support for lora fusion in sd3 * add test to ensure fused lora and effective lora produce same outpouts
-
- 19 Jun, 2024 1 commit
-
-
YiYi Xu authored
fix single file
-
- 18 Jun, 2024 2 commits
-
-
Gæros authored
* [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: -
Dhruv Nair authored
[Single File Loading] Handle unexpected keys in CLIP models when `accelerate` isn't installed. (#8462) * update * update * update * update * update --------- Co-authored-by:
-
- 13 Jun, 2024 1 commit
-
-
Dhruv Nair authored
* update * update
-
- 12 Jun, 2024 1 commit
-
-
Dhruv Nair authored
* up * add sd3 * update * update * add tests * fix copies * fix docs * update * add dreambooth lora * add LoRA * update * update * update * update * import fix * update * Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py Co-authored-by:
-
- 05 Jun, 2024 1 commit
-
-
Sayak Paul authored
* remove legacy code from load_attn_procs. * finish first draft * fix more. * fix more * add test * add serialization support. * fix-copies * require peft backend for lora tests * style * fix test * fix loading. * empty * address benjamin's feedback.
-
- 31 May, 2024 1 commit
-
-
Dhruv Nair authored
update
-
- 29 May, 2024 1 commit
-
-
Sayak Paul authored
* use IPAdapterPlusImageProjectionBlock in IPAdapterPlusImageProjection * reposition IPAdapterPlusImageProjection * refactor complete? * fix heads param retrieval. * update test dict creation method.
-
- 28 May, 2024 1 commit
-
-
Sayak Paul authored
* attempt at fixing onetrainer lora. * fix
-
- 24 May, 2024 1 commit
-
-
Lucain authored
* Fix resume_downoad FutureWarning * only resume download
-
- 22 May, 2024 1 commit
-
-
BootesVoid authored
-
- 12 May, 2024 1 commit
-
-
Sayak Paul authored
fix offload behaviour when device_map is enabled.
-
- 09 May, 2024 2 commits
-
-
Sayak Paul authored
* debugging * save the resulting image * check if order reversing works. * checking values. * up * okay * checking * fix * remove print
-
Dhruv Nair authored
* refactor unet single file loading a bit. * retrieve the unet from create_diffusers_unet_model_from_ldm * update * update * updae * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * tests * update * update * update * Update docs/source/en/api/single_file.md Co-authored-by:
-
- 08 May, 2024 1 commit
-
-
Pierre Dulac authored
SDXL LoRA weights for text encoders should be decoupled on save The method checks if at least one of unet, text_encoder and text_encoder_2 lora weights are passed, which was not reflected in the implentation. Co-authored-by:
-
- 03 May, 2024 1 commit
-
-
Lucain authored
* Deprecate resume_download * align docstring with transformers * style --------- Co-authored-by:
-
- 01 May, 2024 1 commit
-
-
YiYi Xu authored
* up * add comment to the tests + fix dit --------- Co-authored-by:
-
- 25 Apr, 2024 1 commit
-
-
Sayak Paul authored
* fix lora device test * fix more. * fix more/ * quality * empty --------- Co-authored-by:
-
- 22 Apr, 2024 2 commits
-
-
Fabio Rigano authored
* Restore AttnProcessor2_0 in unload_ip_adapter * Fix style * Update test --------- Co-authored-by: -
Jenyuan-Huang authored
* enable control ip-adapter per-transformer block on-the-fly --------- Co-authored-by:
ResearcherXman <xhs.research@gmail.com> Co-authored-by:
-
- 19 Apr, 2024 1 commit
-
-
Fabio Rigano authored
* Switch to peft and multi proj layers * Move Face ID loading and inference to core --------- Co-authored-by:
-
- 12 Apr, 2024 1 commit
-
-
Benjamin Bossan authored
Fix a bug that causes the the call to set_lora_device to ignore the DoRA parameters.
-
- 11 Apr, 2024 1 commit
-
-
Sai-Suraj-27 authored
Fixed deprecated logger.warn with logger.warning.
-
