- 14 Apr, 2025 1 commit
-
-
Yao Matrix authored
loose expected_max_diff from 5e-1 to 8e-1 to make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU Signed-off-by:Matrix Yao <matrix.yao@intel.com>
-
- 13 Apr, 2025 4 commits
-
-
Ishan Modi authored
* added controlnet for sana transformer * improve code quality * addressed PR comments * bug fixes * added test cases * update * added dummy objects * addressed PR comments * update * Forcing update * add to docs * code quality * addressed PR comments * addressed PR comments * update * addressed PR comments * added proper styling * update * Revert "added proper styling" This reverts commit 344ee8a7014ada095b295034ef84341f03b0e359. * manually ordered * Apply suggestions from code review --------- Co-authored-by:Aryan <contact.aryanvs@gmail.com>
-
Tuna Tuncer authored
-
Aryan authored
* HiDream Image * update * -einops * py3.8 * fix -einops * mixins, offload_seq, option_components * docs * Apply style fixes * trigger tests * Apply suggestions from code review Co-authored-by:
😴 * supports_dduf *🤷 🏻 ♂️ * Update src/diffusers/models/transformers/transformer_hidream_image.py Co-authored-by:hlky <hlky@hlky.ac> Co-authored-by:
github-actions[bot] <github-actions[bot]@users.noreply.github.com>
-
Adrien B authored
Correction typo
-
- 12 Apr, 2025 1 commit
-
-
Nikita Starodubcev authored
* add flow matching lcm scheduler * stochastic sampling * upscaling for scale-wise generation * Apply style fixes * Apply suggestions from code review Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
-
- 11 Apr, 2025 4 commits
-
-
hlky authored
* HiDream Image --------- Co-authored-by:
Aryan <aryan@huggingface.co>
-
Tuna Tuncer authored
-
Sayak Paul authored
fix to a constant
-
Sayak Paul authored
relax tolerance for unclip further.
-
- 10 Apr, 2025 9 commits
-
-
Sayak Paul authored
* start cleaning up lora test utils for reusability * update * updates * updates
-
hlky authored
-
Yuqian Hong authored
* fix attention * Apply style fixes --------- Co-authored-by: -
Yao Matrix authored
Signed-off-by: -
xieofxie authored
Co-authored-by:hualxie <hualxie@microsoft.com>
-
Yao Matrix authored
Signed-off-by: -
Yao Matrix authored
Signed-off-by: -
Yao Matrix authored
* fix test_vanilla_funetuning failure on XPU and A100 Signed-off-by:
-
Sayak Paul authored
* support musubi wan loras. * Update src/diffusers/loaders/lora_conversion_utils.py Co-authored-by:
-
- 09 Apr, 2025 13 commits
-
-
YiYi Xu authored
-
Sayak Paul authored
* fix consisid imports * fix opencv import * fix
-
Sayak Paul authored
* fix timeout constant * style * fix
-
Ilya Drobyshevskiy authored
Before this if txt_ids was 3d tensor, line with txt_ids[:1] concat txt_ids by batch dim. Now we first check that txt_ids is 2d tensor (or take first batch element) and then concat by token dim
-
Dhruv Nair authored
* update * update * update * update
-
hlky authored
Co-authored-by:Sayak Paul <spsayakpaul@gmail.com>
-
Yao Matrix authored
* loose test_float16_inference's tolerance from 5e-2 to 6e-2, so XPU can pass UT Signed-off-by:
-
hlky authored
* AutoModel * ... * lol * ... * add test * update * make fix-copies --------- Co-authored-by:Dhruv Nair <dhruv.nair@gmail.com>
-
hlky authored
-
Sayak Paul authored
* fix: SD3 ControlNet validation so that it runs on a A100. * use backend-agnostic cache and pass devide.
-
Sayak Paul authored
* support more comyui loras. * fix * fixes * revert changes in LoRA base. * no position_embedding *
🚨 introduce a breaking change to let peft handle module ambiguity * styling * remove position embeddings. * improvements. * style * make info instead of NotImplementedError * Update src/diffusers/loaders/peft.py Co-authored-by: -
Sayak Paul authored
minor updates to dtype map docs.
-
Sayak Paul authored
-
- 08 Apr, 2025 8 commits
-
-
Sayak Paul authored
* improve replacement warnings for bnb * updates to docs.
-
Sayak Paul authored
* implement record_stream for better performance. * fix * style. * merge #11097 * Update src/diffusers/hooks/group_offloading.py Co-authored-by:
-
hlky authored
* Flux quantized with lora * fix * changes * Apply suggestions from code review Co-authored-by:
-
Linoy Tsaban authored
* remove custom scheduler * update requirements.txt * log_validation with mixed precision * add intermediate embeddings saving when checkpointing is enabled * remove comment * fix validation * add unwrap_model for accelerator, torch.no_grad context for validation, fix accelerator.accumulate call in advanced script * revert unwrap_model change temp * add .module to address distributed training bug + replace accelerator.unwrap_model with unwrap model * changes to align advanced script with canonical script * make changes for distributed training + unify unwrap_model calls in advanced script * add module.dtype fix to dreambooth script * unify unwrap_model calls in dreambooth script * fix condition in validation run * mixed precision * Update examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py Co-authored-by:
-
Yao Matrix authored
* add arch specfic expectations support, to support different arch's numerical characteristics Signed-off-by:
-
Benjamin Bossan authored
* [WIP][LoRA] Implement hot-swapping of LoRA This PR adds the possibility to hot-swap LoRA adapters. It is WIP. Description As of now, users can already load multiple LoRA adapters. They can offload existing adapters or they can unload them (i.e. delete them). However, they cannot "hotswap" adapters yet, i.e. substitute the weights from one LoRA adapter with the weights of another, without the need to create a separate LoRA adapter. Generally, hot-swapping may not appear not super useful but when the model is compiled, it is necessary to prevent recompilation. See #9279 for more context. Caveats To hot-swap a LoRA adapter for another, these two adapters should target exactly the same layers and the "hyper-parameters" of the two adapters should be identical. For instance, the LoRA alpha has to be the same: Given that we keep the alpha from the first adapter, the LoRA scaling would be incorrect for the second adapter otherwise. Theoretically, we could override the scaling dict with the alpha values derived from the second adapter's config, but changing the dict will trigger a guard for recompilation, defeating the main purpose of the feature. I also found that compilation flags can have an impact on whether this works or not. E.g. when passing "reduce-overhead", there will be errors of the type: > input name: arg861_1. data pointer changed from 139647332027392 to 139647331054592 I don't know enough about compilation to determine whether this is problematic or not. Current state This is obviously WIP right now to collect feedback and discuss which direction to take this. If this PR turns out to be useful, the hot-swapping functions will be added to PEFT itself and can be imported here (or there is a separate copy in diffusers to avoid the need for a min PEFT version to use this feature). Moreover, more tests need to be added to better cover this feature, although we don't necessarily need tests for the hot-swapping functionality itself, since those tests will be added to PEFT. Furthermore, as of now, this is only implemented for the unet. Other pipeline components have yet to implement this feature. Finally, it should be properly documented. I would like to collect feedback on the current state of the PR before putting more time into finalizing it. * Reviewer feedback * Reviewer feedback, adjust test * Fix, doc * Make fix * Fix for possible g++ error * Add test for recompilation w/o hotswapping * Make hotswap work Requires https://github.com/huggingface/peft/pull/2366 More changes to make hotswapping work. Together with the mentioned PEFT PR, the tests pass for me locally. List of changes: - docstring for hotswap - remove code copied from PEFT, import from PEFT now - adjustments to PeftAdapterMixin.load_lora_adapter (unfortunately, some state dict renaming was necessary, LMK if there is a better solution) - adjustments to UNet2DConditionLoadersMixin._process_lora: LMK if this is even necessary or not, I'm unsure what the overall relationship is between this and PeftAdapterMixin.load_lora_adapter - also in UNet2DConditionLoadersMixin._process_lora, I saw that there is no LoRA unloading when loading the adapter fails, so I added it there (in line with what happens in PeftAdapterMixin.load_lora_adapter) - rewritten tests to avoid shelling out, make the test more precise by making sure that the outputs align, parametrize it - also checked the pipeline code mentioned in this comment: https://github.com/huggingface/diffusers/pull/9453#issuecomment-2418508871; when running this inside the with torch._dynamo.config.patch(error_on_recompile=True) context, there is no error, so I think hotswapping is now working with pipelines. * Address reviewer feedback: - Revert deprecated method - Fix PEFT doc link to main - Don't use private function - Clarify magic numbers - Add pipeline test Moreover: - Extend docstrings - Extend existing test for outputs != 0 - Extend existing test for wrong adapter name * Change order of test decorators parameterized.expand seems to ignore skip decorators if added in last place (i.e. innermost decorator). * Split model and pipeline tests Also increase test coverage by also targeting conv2d layers (support of which was added recently on the PEFT PR). * Reviewer feedback: Move decorator to test classes ... instead of having them on each test method. * Apply suggestions from code review Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> --------- Co-authored-by:
-
Álvaro Somoza authored
* initial * Update examples/dreambooth/train_dreambooth_lora_sdxl.py Co-authored-by:
-
Bhavay Malhotra authored
[train_controlnet.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#8461) * Create diffusers.yml * fix num_train_epochs * Delete diffusers.yml * Fixed Changes --------- Co-authored-by:
-
