- 02 Nov, 2023 1 commit
-
-
Dhruv Nair authored
* draft design * clean up * clean up * clean up * clean up * clean up * clean up * clean up * clean up * clean up * update pipeline * clean up * clean up * clean up * add tests * change motion block * clean up * clean up * clean up * update * update * update * update * update * update * update * update * clean up * update * update * update model test * update * update * update * update * make style * update * fix embeddings * update * merge upstream * max fix copies * fix bug * fix mistake * add docs * update * clean up * update * clean up * clean up * fix docstrings * fix docstrings * update * update * clean up * update
-
- 01 Nov, 2023 4 commits
-
-
Patrick von Platen authored
* fix * fix
-
Patrick von Platen authored
-
ilisparrow authored
* Enable lora for sdxl adapters too. Issue #5516 * fix: assertion values. * Use numpy_cosine_similarity_distance on the arrays Co-authored-by:
Dhruv Nair <dhruv.nair@gmail.com> * Use numpy_cosine_similarity_distance on the arrays Co-authored-by:
Ilias A <iliasamri00@gmail.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
clarencechen authored
* 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
-
- 30 Oct, 2023 3 commits
-
-
Aryan V S authored
* update * update * update * update
-
Peter @sHTiF Stefcek authored
-
Patrick von Platen authored
* finish * finish
-
- 27 Oct, 2023 1 commit
-
-
Sayak Paul authored
* disable freeu debug * debug * potentially fix. * finish * manually remove the spaces * remove tab
-
- 26 Oct, 2023 1 commit
-
-
Patrick von Platen authored
* upload custom remote poc * up * make style * finish * better name * Apply suggestions from code review * Update tests/pipelines/test_pipelines.py * more fixes * remove ipdb * more fixes * fix more * finish tests --------- Co-authored-by:
-
- 25 Oct, 2023 4 commits
-
-
Patrick von Platen authored
-
Aryan V S authored
* improvement: add typehints and docs to src/diffusers/models/attention_processor.py * improvement: add typehints and docs to src/diffusers/models/vae.py * improvement: add missing docs in src/diffusers/models/vq_model.py * improvement: add typehints and docs to src/diffusers/models/transformer_temporal.py * improvement: add typehints and docs to src/diffusers/models/t5_film_transformer.py * improvement: add type hints to src/diffusers/models/unet_1d_blocks.py * improvement: add missing type hints to src/diffusers/models/unet_2d_blocks.py * fix: CI error (make fix-copies required) * fix: CI error (make fix-copies required again) --------- Co-authored-by: -
Patrick von Platen authored
* [Schedulers] Fix 2nd order other than heun * Apply suggestions from code review
-
YiYi Xu authored
* fix * fix copies * remove heun from tests * add back heun and fix the tests to include 2nd order * fix the other test too * Apply suggestions from code review * Apply suggestions from code review * Apply suggestions from code review * make style * add more comments --------- Co-authored-by:
yiyixuxu <yixu310@gmail,com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com>
-
- 24 Oct, 2023 2 commits
-
-
dg845 authored
* initial commit for LatentConsistencyModelPipeline and LCMScheduler based on the community pipeline * Add callback and freeu support. * apply suggestions from review * Clean up LCMScheduler * Remove timeindex argument to LCMScheduler.step. * Add support for clipping or thresholding the predicted original sample. * Remove unused methods and arguments in LCMScheduler. * Improve comment about (lack of) negative prompt support. * Change input guidance_scale to match the StableDiffusionPipeline (Imagen) CFG formulation. * Move lcm_origin_steps from pipeline __call__ to LCMScheduler.__init__/config (as origin_steps). * Fix typo when clipping/thresholding in LCMScheduler. * Add some initial LCMScheduler tests. * add type annotations from review * Fix type annotation bug. * Override test_add_noise_device in LCMSchedulerTest since hardcoded timesteps doesn't work under default settings. * Add generator argument pipeline prepare_latents call. * Cast LCMScheduler.timesteps to long in set_timesteps. * Add onestep and multistep full loop scheduler tests. * Set default height/width to None and don't hardcode guidance scale embedding dim. * Add initial LatentConsistencyPipeline fast and slow tests. * Add initial documentation for LatentConsistencyModelPipeline and LCMScheduler. * Make remaining failing fast tests pass. * make style * Make original_inference_steps configurable from pipeline __call__ again. * make style * Remove guidance_rescale arg from pipeline __call__ since LCM currently doesn't support CFG. * Make LCMScheduler defaults match config of LCM_Dreamshaper_v7 checkpoint. * Fix LatentConsistencyPipeline slow tests and add dummy expected slices. * Add checks for original_steps in LCMScheduler.set_timesteps. * make fix-copies * Improve LatentConsistencyModelPipeline docs. * Apply suggestions from code review Co-authored-by:
Aryan V S <avs050602@gmail.com> * Apply suggestions from code review Co-authored-by:
-
Sayak Paul authored
* move out the activations. * move normalization layers. * add doc. * add doc. * fix: paths * Apply suggestions from code review Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> * style --------- Co-authored-by:
-
- 23 Oct, 2023 3 commits
-
-
YiYi Xu authored
* add * Update docs/source/en/api/pipelines/controlnet_sdxl.md Co-authored-by:
-
Sayak Paul authored
* fix: controlnet graph? * fix: sample * fix: * remove print * styling * fix-copies * prevent more graph breaks? * prevent more graph breaks? * see? * revert. * compilation. * rpopagate changes to controlnet sdxl pipeline too. * add: clean version checking.
-
Ryan Dick authored
* Update get_dummy_inputs(...) in T2I-Adapter tests to take image height and width as params. * Update the T2I-Adapter unit tests to run with the standard number of UNet down blocks so that all T2I-Adapter down blocks get exercised. * Update the T2I-Adapter down blocks to better match the padding behavior of the UNet. * Revert "Update the T2I-Adapter unit tests to run with the standard number of UNet down blocks so that all T2I-Adapter down blocks get exercised." This reverts commit 6d4a060a34415ec973a252944216f4fb8b9926cd. * Create utility functions for testing the T2I-Adapter downscaling bahevior. * (minor) Improve readability with an intermediate named variable. * Statically parameterize T2I-Adapter test dimensions rather than generating them dynamically. * Fix static checks. --------- Co-authored-by:
-
- 21 Oct, 2023 1 commit
-
-
Younes Belkada authored
* fix scale unscale v1 * final fixes + CI * fix slow trst * oops * fix copies * oops * oops * fix * style * fix copies --------- Co-authored-by:
-
- 20 Oct, 2023 1 commit
-
-
Vishnu V Jaddipal authored
* Added args, kwargs to ```U * Add UNetMidBlock2D as a supported mid block type * Fix extra init input for UNetMidBlock2D, change allowed types for Mid-block init * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_condition.py * Update unet_2d_blocks.py * Update unet_2d_blocks.py * Update unet_2d_blocks.py * Update unet_2d_condition.py * Update unet_2d_blocks.py * Updated docstring, increased check strictness Updated the docstring for ```UNet2DConditionModel``` to include ```reverse_transformer_layers_per_block``` and updated checking for nested list type ```transformer_layers_per_block``` * Add basic shape-check test for asymmetrical unets * Update src/diffusers/models/unet_2d_blocks.py Removed blank line Co-authored-by:
-
- 18 Oct, 2023 4 commits
-
-
Patrick von Platen authored
-
__mo_san__ authored
* added TODOs * Enhanced and reformatted the docstrings of IFPipeline methods. * Enhanced and fixed the docstrings of IFImg2ImgSuperResolutionPipeline methods. * Enhanced and fixed the docstrings of IFImg2ImgPipeline methods. * Enhanced and fixed the docstrings of IFInpaintingSuperResolutionPipeline methods. * Enhanced and fixed the docstrings of IFInpaintingPipeline methods. * Enhanced and fixed the docstrings of IFSuperResolutionPipeline methods. * Update src/diffusers/pipelines/deepfloyd_if/pipeline_if.py Co-authored-by:
-
Sayak Paul authored
fix: local single file loading.
-
Patrick von Platen authored
-
- 17 Oct, 2023 1 commit
-
-
Sayak Paul authored
* fix: sdxl pipeline when unet is not available. * fix moe * account for text * ifx more * don't make unet optional. * Apply suggestions from code review Co-authored-by:
-
- 16 Oct, 2023 4 commits
-
-
Patrick von Platen authored
-
Gregg Helt authored
* Add ability to mix usage of T2I-Adapter(s) and ControlNet(s). Previously, UNet2DConditional implemnetation onloy allowed use of one or the other. Adds new forward() arg down_intrablock_additional_residuals specifically for T2I-Adapters. If down_intrablock_addtional_residuals is not used, maintains backward compatibility with prior usage of only T2I-Adapter or ControlNet but not both * Improving forward() arg docs in src/diffusers/models/unet_2d_condition.py Co-authored-by:
psychedelicious <4822129+psychedelicious@users.noreply.github.com> * Add deprecation warning if down_block_additional_residues is used for T2I-Adapter (intrablock residuals) Co-authored-by:
-
Heinz-Alexander Fuetterer authored
* chore: fix typos * Update src/diffusers/pipelines/shap_e/renderer.py Co-authored-by:
-
Kashif Rasul authored
* initial script * formatting * prior trainer wip * add efficient_net_encoder * add CLIPTextModel * add prior ema support * optimizer * fix typo * add dataloader * prompt_embeds and image_embeds * intial training loop * fix output_dir * fix add_noise * accelerator check * make effnet_transforms dynamic * fix training loop * add validation logging * use loaded text_encoder * use PreTrainedTokenizerFast * load weigth from pickle * save_model_card * remove unused file * fix typos * save prior pipeilne in its own folder * fix imports * fix pipe_t2i * scale image_embeds * remove snr_gamma * format * initial lora prior training * log_validation and save * initial gradient working * remove save/load hooks * set set_attn_processor on prior_prior * add lora script * typos * use LoraLoaderMixin for prior pipeline * fix usage * make fix-copies * yse repo_id * write_lora_layers is a staitcmethod * use defualts * fix defaults * undo * Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py Co-authored-by:
Pedro Cuenca <pedro@huggingface.co> * Update examples/wuerstchen/text_to_image/README.md Co-authored-by:
-
- 13 Oct, 2023 2 commits
-
-
Younes Belkada authored
* v1 * add tests and fix previous failing tests * fix CI * add tests + v1 `PeftLayerScaler` * style * add scale retrieving mechanism system * fix CI * up * up * simple approach --> not same results for some reason * fix issues * fix copies * remove unneeded method * active adapters! * fix merge conflicts * up * up * kohya - test-1 * Apply suggestions from code review Co-authored-by:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com> * Update src/diffusers/models/attention.py Co-authored-by:
Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com> Co-authored-by:
-
Sayak Paul authored
* add: freeu to the core sdxl pipeline. * add: freeu to video2video * add: freeu to the core SD pipelines. * add: freeu to image variation for sdxl. * add: freeu to SD ControlNet pipelines. * add: freeu to SDXL controlnet pipelines. * add: freu to t2i adapter pipelines. * make fix-copies.
-
- 11 Oct, 2023 1 commit
-
-
ssusie authored
* Added mark_step for sdxl to run with pytorch xla. Also updated README with instructions for xla * adding soft dependency on torch_xla * fix some styling --------- Co-authored-by:
-
- 09 Oct, 2023 5 commits
-
-
Roy Hvaara authored
`jnp.array` is a function, not a type: https://jax.readthedocs.io/en/latest/_autosummary/jax.numpy.array.html so it never makes sense to use `jnp.array` in a type annotation. Presumably the intent was to write `jnp.ndarray` aka `jax.Array`. Change uses of `jnp.array` to `jnp.ndarray`. Co-authored-by:
Peter Hawkins <phawkins@google.com>
-
Jake Vanderplas authored
-
Patrick von Platen authored
-
Aryan V S authored
* add missing docstrings * chore: run make quality * improvement: include docs suggestion by @yiyixuxu --------- Co-authored-by: -
chuzh authored
Fix [core/GLIGEN]: TypeError when iterating over 0-d tensor with In-painting mode when EulerAncestralDiscreteScheduler is used (#5305) * fix(gligen_inpaint_pipeline):
🐛 Wrap the timestep() 0-d tensor in a list to convert to 1-d tensor. This avoids the TypeError caused by trying to directly iterate over a 0-dimensional tensor in the denoising stage * test(gligen/gligen_text_image): unit test using the EulerAncestralDiscreteScheduler --------- Co-authored-by:zhen-hao.chu <zhen-hao.chu@vitrox.com> Co-authored-by:
-
- 06 Oct, 2023 2 commits
-
-
vedant2003 authored
* Update pipeline_wuerstchen_prior.py * prior_num_inference_steps updated * height, width, num_inference_steps, and guidance_scale synced * parameters synced * latent_mean, latent_std, and resolution_multiple synced * prior_num_inference_steps changed * Formatted pipeline_wuerstchen_prior.py * Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py --------- Co-authored-by:Kashif Rasul <kashif.rasul@gmail.com>
-
Dhruv Nair authored
Add from single file to StableDiffusionUpscalePipeline and StableDiffusionLatentUpscalePipeline (#5194) * add from single file * clean up * make style * add single file loading for upscaling
-
