Add UniDiffuser model and pipeline #2963

* Fix a bug of pano when not doing CFG * enhance code quality * apply formatting. --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* fix progress bar issue in pipeline_text_to_video_zero.py. Copy scheduler after first backward * fix tensor loading in test_text_to_video_zero.py * make style && make quality

* fix: norm group test for UNet3D. * chore: speed up the panorama tests (fast). * set default value of _test_inference_batch_single_identical. * fix: batch_sizes default value.

* WIP controlnet training - bugfix --streaming - bugfix running report_to!='wandb' - adds memory profile before validation * Adds final logging statement. * Sets train epochs to 11. Looking at a longer ~16ep run, we see only good validation images after ~11ep: https://wandb.ai/andsteing/controlnet_fill50k/runs/3j2hx6n8 * Removes --logging_dir (it's not used). * Adds --profile flags. * Updates --output_dir=runs/fill-circle-{timestamp}. * Compute mean of `train_metrics`. Previously `train_metrics[-1]` was logged, resulting in very bumpy train metrics. * Improves logging a bit. - adds l2_grads gradient norm logging - adds steps_per_sec - sets walltime as x coordinate of train/step - logs controlnet_params config * Adds --ccache (doesn't really help though). * minor fix in controlnet flax example (huggingface#2986) * fix the error when push_to_hub but not log validation * contronet_from_pt & controlnet_revision * add intermediate checkpointing to the guide * Bugfix --profile_steps * Sets `RACKER_PROJECT_NAME='controlnet_fill50k'`. * Logs fractional epoch. * Adds relative `walltime` metric. * Adds `StepTraceAnnotation` and uses `global_step` insetad of `step`. * Applied `black`. * Streamlines commands in README a bit. * Removes `--ccache`. This makes only a very small difference (~1 min) with this model size, so removing the option introduced in cdb3cc. * Re-ran `black`. * Update examples/controlnet/README.md Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * Converts spaces to tab. * Removes repeated args. * Skips first step (compilation) in profiling * Updates README with profiling instructions. * Unifies tabs/spaces in README. * Re-ran style & quality. --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

…ggingface#3080)

* [Tests] parallelize * finish folder structuring * Parallelize tests more * Correct saving of pipelines * make sure logging level is correct * try again * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> --------- Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Throw deprecation warning

…es (huggingface#2835) Allow stable diffusion attend and excite pipeline to work with any size output image. Re: huggingface#2476, huggingface#2603

* update community pipeline docs * fix formatting * explain sharing workflows

…gingface#2998) * add guess mode (WIP) * fix uncond/cond order * support guidance_scale=1.0 and batch != 1 * remove magic coeff * add docstring * add intergration test * add document to controlnet.mdx * made the comments a bit more explanatory * fix table

* fix default

remvoe one line

add custom timesteps test add custom timesteps descending order check docs timesteps -> custom_timesteps can only pass one of num_inference_steps and timesteps

…gingface#3118) fix breaking change

Fix img2img processor with safety checker

…face#3128) Make sure correct timesteps are chosen for img2img

* Better deprecation message * Better deprecation message * Better doc string * Fixes * fix more * fix more * Improve __getattr__ * correct more * fix more * fix * Improve more * more improvements * fix more * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * make style * Fix all rest & add tests & remove old deprecation fns --------- Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

…ace#3126) * feat: verfication of multi-gpu support for select examples. * add: multi-gpu training sections to the relvant doc pages.

extract pipeline from log_validation

* Update README.md * Apply suggestions from code review

Adding act fn config to the unet timestep class embedding and conv activation. The custom activation defaults to silu which is the default activation function for both the conv act and the timestep class embeddings so default behavior is not changed. The only unet which use the custom activation is the stable diffusion latent upscaler https://huggingface.co/stabilityai/sd-x2-latent-upscaler/blob/main/unet/config.json (I ran a script against the hub to confirm). The latent upscaler does not use the conv activation nor the timestep class embeddings so we don't change its behavior.

) This mimics the dtype cast for the standard time embeddings

…loading a ckpt model (huggingface#2705) * [ckpt loader] Allow loading the Inpaint and Img2Img pipelines, while loading a ckpt model * Address review comment from PR * PyLint formatting * Some more pylint fixes, unrelated to our change * Another pylint fix * Styling fix

* add mixin class for pipeline from original sd ckpt * Improve * make style * merge main into * Improve more * fix more * up * Apply suggestions from code review * finish docs * rename * make style --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

…nsorRT utils (huggingface#2974) * Add SD/txt2img Community Pipeline to diffusers along with TensorRT utils Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * update installation command Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * update tensorrt installation Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * changes 1. Update setting of cache directory 2. Address comments: merge utils and pipeline code. 3. Address comments: Add section in README Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * apply make style Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> --------- Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

⚙️chore(transformer_2d) update function signature for encoder_hidden_states

* Update pipeline_stable_diffusion_inpaint_legacy.py * fix preprocessing of Pil images with adequate batch size * revert map * add tests * reformat * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * next try to fix the style * wth is this * Update testing_utils.py * Update testing_utils.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

…e#2993) * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 * Modified altdiffusion pipline to support altdiffusion-m18 --------- Co-authored-by: root <fulong_ye@163.com>

controlnet training center crop input images to multiple of 8 The pipeline code resizes inputs to multiples of 8. Not doing this resizing in the training script is causing the encoded image to have different height/width dimensions than the encoded conditioning image (which uses a separate encoder that's part of the controlnet model). We resize and center crop the inputs to make sure they're the same size (as well as all other images in the batch). We also check that the initial resolution is a multiple of 8.

) * diffusers==0.14.0 update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion * custom diffusion * custom diffusion * custom diffusion * custom diffusion * apply formatting and get rid of bare except. * refactor readme and other minor changes. * misc refactor. * fix: repo_id issue and loaders logging bug. * fix: save_model_card. * fix: save_model_card. * fix: save_model_card. * add: doc entry. * refactor doc,. * custom diffusion * custom diffusion * custom diffusion * apply style. * remove tralining whitespace. * fix: toctree entry. * remove unnecessary print. * custom diffusion * custom diffusion * custom diffusion test * custom diffusion xformer update * custom diffusion xformer update * custom diffusion xformer update --------- Co-authored-by: Nupur Kumari <nupurkumari@Nupurs-MacBook-Pro.local> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Nupur Kumari <nupurkumari@nupurs-mbp.wifi.local.cmu.edu>

Add missing newlines for rendering the links correctly

…ggingface#2760) * Added distillation for quantization example on textual inversion. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * refined readme and code style. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * Update text2images.py * refined code of model load and added compatibility check. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * fixed code style. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * fix C403 [*] Unnecessary `list` comprehension (rewrite as a `set` comprehension) Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> --------- Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

…uggingface#2942) * Update Pix2PixZero Auto-correlation Loss * Add fast inversion tests * Clarify purpose and mark as deprecated Fix inversion prompt broadcasting * Register modules set to `None` in config for `test_save_load_optional_components` * Update new tests to coordinate with huggingface#2953

… script (huggingface#3130) * add: LoRA text encoder support for DreamBooth example. * fix initialization. * fix: modification call. * add: entry in the readme. * use dog dataset from hub. * fix: params to clip. * add entry to the LoRA doc. * add: tests for lora. * remove unnecessary list comprehension./

* Update Habana Gaudi doc * Fix tables

* Add model offload to x4 upscaler * fix

deterministic algos

* Update custom_diffusion.mdx * fix: unnecessary list comprehension.

pass silence_dtype_warnings as kwarg Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

fix from_flax Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* clarify training arg * apply feedback

* Multi Vector * Improve * fix multi token * improve test * make style * Update examples/test_examples.py * Apply suggestions from code review Co-authored-by: Suraj Patil <surajp815@gmail.com> * update * Finish * Apply suggestions from code review --------- Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add karras pattern to discrete heun scheduler * Add integration test * Fix failing CI on pytorch test on M1 (mps) --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update train_dreambooth_lora.py fix bug * Update train_dreambooth_lora.py

…ce#3197) * Update lpw_stable_diffusion.py * fix cpu offload

* Make sure attention works with Torch 2_0 * make style * Fix more

…uggingface#3201) Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline (huggingface#3197)" This reverts commit 9965cb5.

…gface#3138) cast to weight dtype

…e#3225) adding enable_vae_tiling and disable_val_tiling functions

Add v1.1 docs

When the token used for textual inversion does not have any special symbols (e.g. it is not surrounded by <>), the tokenizer does not properly split the replacement tokens. Adding a space for the padding tokens fixes this.

sync cache version check from transformers

* Fix docs text inversion * Apply suggestions from code review

* add * clean * up * clean up more * fix more tests * Improve docs further * improve * more fixes docs * Improve docs more * Update src/diffusers/models/unet_2d_condition.py * fix * up * update doc links * make fix-copies * add safety checker and watermarker to stage 3 doc page code snippets * speed optimizations docs * memory optimization docs * make style * add watermarking snippets to doc string examples * make style * use pt_to_pil helper functions in doc strings * skip mps tests * Improve safety * make style * new logic * fix * fix bad onnx design * make new stable diffusion upscale pipeline model arguments optional * define has_nsfw_concept when non-pil output type * lowercase linked to notebook name --------- Co-authored-by: William Berman <WLBberman@gmail.com>

* Add all files * update

* Add all files * update * Make sure vae is memory efficient for PT 1 * make style

* add document on token merging. * fix headline. * fix: headline. * add some samples for comparison.

* [AudioLDM] Update docs to use updated ckpt * make style

* Post release * fix more

* [docs] only mention one stage * add blurb on auto accepting --------- Co-authored-by: William Berman <WLBberman@gmail.com>

Write model card in controlnet training script.

* [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * [2064]: Add stochastic sampler * Review comments * [Review comment]: Add is_torchsde_available() * [Review comment]: Test and docs * [Review comment] * [Review comment] * [Review comment] * [Review comment] * [Review comment] --------- Co-authored-by: njindal <njindal@adobe.com>

[Slow Test]: Cuda test fixes Co-authored-by: njindal <njindal@adobe.com>

Remove required from tracker_project_name. As observed by https://github.com/off99555 in huggingface#2695 (comment), it already has a default value.

…n_block (huggingface#3210) * removed unnecessary parameters from get_up_block and get_down_block functions * adding resnet_skip_time_act, resnet_out_scale_factor and cross_attention_norm to get_up_block and get_down_block functions --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

Update repaint.mdx accomodate to huggingface#1701

Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com>

The pipeline is built as `pipe` but then used as `pipeline`.

…ingface#3114) * config fixes * deprecate get_input_dims

…eline"" (huggingface#3265) Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline" (huggingface#3201)" This reverts commit 91a2a80.

Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>

* [docs] add notes for stateful model changes * Update docs/source/en/optimization/fp16.mdx Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * link to accelerate docs for discarding hooks --------- Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

…huggingface#3180) * 👽 qol improvements for LoRA. * better function name? * fix: LoRA weight loading with the new format. * address Patrick's comments. * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * change wording around encouraging the use of load_lora_weights(). * fix: function name. --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* EDICT pipeline initial commit - Starting point taking from https://github.com/Joqsan/edict-diffusion * refactor __init__() method * minor refactoring * refactor scheduler code - remove scheduler and move its methods to the EDICTPipeline class * make CFG optional - refactor encode_prompt(). - include optional generator for sampling with vae. - minor variable renaming * add EDICT pipeline description to README.md * replace preprocess() with VaeImageProcessor * run make style and make quality commands --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* zh translated docs update * update _toctree

Fix typos

…uggingface#3125) * try multi controlnet inpaint * multi controlnet inpaint * multi controlnet inpaint

…e#3272) * Update Dreambooth README * Adapt all docs as well * automatically write model card * fix * make style

* Update Pix2PixZero Auto-correlation Loss * Add Stable Diffusion DiffEdit pipeline * Add draft documentation and import code * Bugfixes and refactoring * Add option to not decode latents in the inversion process * Harmonize preprocessing * Revert "Update Pix2PixZero Auto-correlation Loss" This reverts commit b218062. * Update annotations * rename `compute_mask` to `generate_mask` * Update documentation * Update docs * Update Docs * Fix copy * Change shape of output latents to batch first * Update docs * Add first draft for tests * Bugfix and update tests * Add `cross_attention_kwargs` support for all pipeline methods * Fix Copies * Add support for PIL image latents Add support for mask broadcasting Update docs and tests Align `mask` argument to `mask_image` Remove height and width arguments * Enable MPS Tests * Move example docstrings * Fix test * Fix test * fix pipeline inheritance * Harmonize `prepare_image_latents` with StableDiffusionPix2PixZeroPipeline * Register modules set to `None` in config for `test_save_load_optional_components` * Move fixed logic to specific test class * Clean changes to other pipelines * Update new tests to coordinate with huggingface#2953 * Update slow tests for better results * Safety to avoid potential problems with torch.inference_mode * Add reference in SD Pipeline Overview * Fix tests again * Enforce determinism in noise for generate_mask * Fix copies * Widen test tolerance for fp16 based on `test_stable_diffusion_upscale_pipeline_fp16` * Add LoraLoaderMixin and update `prepare_image_latents` * clean up repeat and reg * bugfix * Remove invalid args from docs Suppress spurious warning by repeating image before latent to mask gen

* add constant lr with rules * add constant with rules in TYPE_TO_SCHEDULER_FUNCTION * add constant lr rate with rule * hotfix code quality * fix doc style * change name constant_with_rules to piecewise constant

* Allow disabling torch 2_0 attention * make style * Update src/diffusers/models/attention.py

add link to training script Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>

The note-seq package throws an error on import because the default installed version of Ipython is not compatible with python 3.8 which we run in the CI. https://github.com/huggingface/diffusers/actions/runs/4830121056/jobs/8605954838#step:7:9

A pipeline object stores the results in `images` not in `sample`. Current code blocks don't work.

* fix more * Fix more * fix more * Apply suggestions from code review * fix * make style * make fix-copies * fix * make sure torch compile * Clean * fix test

* refactor img2img VaeImageProcessor.postprocess * remove copy from for init, run_safety_checker, decode_latents Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> --------- Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Fix more torch compile breaks * add tests * Fix all * fix controlnet * fix more * Add Horace He as co-author. > > Co-authored-by: Horace He <horacehe2007@yahoo.com> * Add Horace He as co-author. Co-authored-by: Horace He <horacehe2007@yahoo.com> --------- Co-authored-by: Horace He <horacehe2007@yahoo.com>

* fix: scale_lr and sync example readme and docs. * fix doc link.

fixed import statement

Fix missing variable assign lol

Update build_documentation.yml

* Add Stable Diffsuion RePaint to community pipelines - Adds Stable Diffsuion RePaint to community pipelines - Add Readme enty for pipeline * Fix: Remove wrong import - Remove wrong import - Minor change in comments * Fix: Code formatting of stable_diffusion_repaint * Fix: ruff errors in stable_diffusion_repaint

…f) (huggingface#3314) * fix multistep dpmsolver for cosine schedule (deepfloy-if) * fix a typo * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * update all dpmsolver (singlestep, multistep, dpm, dpm++) for cosine noise schedule * add test, fix style --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* update docs * add to toctree * apply feedback

* Added input pretubation * Fixed spelling

)

* add SDE variant of DPM-Solver and DPM-Solver++ * add test * fix typo * fix typo

The argument `upsample_size` needs to be added to these modules to allow compatibility with other blocks that require this argument.

…o support pre- and post-LN, add fast default tests, fix some bugs.

…tter match the reference UniDiffuser implementation.

This reverts commit 10a174a.

…d to CPU in the enable_sequential_cpu_offload(...)/enable_model_cpu_offload(...) methods to make test_cpu_offload_forward_pass pass.

- Improve batch size inference and fix bugs when num_images_per_prompt or num_prompts_per_image > 1 - Add tests for num_images_per_prompt, num_prompts_per_image > 1 - Improve check_inputs, especially regarding checking supplied latents - Add reset_mode method so that mode inference can be re-enabled after mode is set manually - Fix some warnings related to accessing class members directly instead of through their config - Small amount of refactoring in pipeline_unidiffuser.py

…so do some light refactoring.

…cstrings.

…s/convert_unidiffuser_to_diffusers.py

…peline __init__.py

…torch operations.

…image slices/text prefixes.

…ch.autocast context manager.

… the torch.autocast context manager." This reverts commit 1a58958.

…e cuda/fp16 functionality.

…age_encoder to better match the original UniDiffuser implementation.

…fix issue in modeling_text_decoder.py.

…e slow tests with new expected outputs.

…n instead of always getting its mode.

… VAE's scaling factor.

fix docstring Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* update IF stage I pipelines add fixed variance schedulers and lora loading * added kv lora attn processor * allow loading into alternative lora attn processor * make vae optional * throw away predicted variance * allow loading into added kv lora layer * allow load T5 * allow pre compute text embeddings * set new variance type in schedulers * fix copies * refactor all prompt embedding code class prompts are now included in pre-encoding code max tokenizer length is now configurable embedding attention mask is now configurable * fix for when variance type is not defined on scheduler * do not pre compute validation prompt if not present * add example test for if lora dreambooth * add check for train text encoder and pre compute text embeddings

* add text2img * fix-copies * add * add all other pipelines * add * add * add * add * add * make style * style + fix copies --------- Co-authored-by: yiyixuxu <yixu310@gmail,com>

* clarify safetensor docstring * fix typo * apply feedback

…ace#3365) * add: a warning message when using xformers in a PT 2.0 env. * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

…th (huggingface#3322) * StableDiffusionInpaintingPipeline now resizes input images and masks w.r.t to passed input height and width. Default is already set to 512. This addresses the common tensor mismatch error. Also moved type check into relevant funciton to keep main pipeline body tidy. * Fixed StableDiffusionInpaintingPrepareMaskAndMaskedImageTests Due to previous commit these tests were failing as height and width need to be passed into the prepare_mask_and_masked_image function, I have updated the code and added a height/width variable per unit test as it seemed more appropriate than the current hard coded solution * Added a resolution test to StableDiffusionInpaintPipelineSlowTests this unit test simply gets the input and resizes it into some that would fail (e.g. would throw a tensor mismatch error/not a mult of 8). Then passes it through the pipeline and verifies it produces output with correct dims w.r.t the passed height and width --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* first draft * apply feedback * conv_in.weight thrown away

* safetensors * apply feedback * apply feedback * Apply suggestions from code review --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Fix typo in last code block. Correct "prommpts" to "prompt"

* add inferring_controlnet_cond_batch * Revert "add inferring_controlnet_cond_batch" This reverts commit abe8d63. * set guess_mode to True whenever global_pool_conditions is True Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * nit * add integration test --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* enable deterministic pytorch and cuda operations. * disable manual seeding. * make style && make quality for unet_2d tests. * enable determinism for the unet2dconditional model. * add CUBLAS_WORKSPACE_CONFIG for better reproducibility. * relax tolerance (very weird issue, though). * revert to torch manual_seed() where needed. * relax more tolerance. * better placement of the cuda variable and relax more tolerance. * enable determinism for 3d condition model. * relax tolerance. * add: determinism to alt_diffusion. * relax tolerance for alt diffusion. * dance diffusion. * dance diffusion is flaky. * test_dict_tuple_outputs_equivalent edit. * fix two more tests. * fix more ddim tests. * fix: argument. * change to diff in place of difference. * fix: test_save_load call. * test_save_load_float16 call. * fix: expected_max_diff * fix: paint by example. * relax tolerance. * add determinism to 1d unet model. * torch 2.0 regressions seem to be brutal * determinism to vae. * add reason to skipping. * up tolerance. * determinism to vq. * determinism to cuda. * determinism to the generic test pipeline file. * refactor general pipelines testing a bit. * determinism to alt diffusion i2i * up tolerance for alt diff i2i and audio diff * up tolerance. * determinism to audioldm * increase tolerance for audioldm lms. * increase tolerance for paint by paint. * increase tolerance for repaint. * determinism to cycle diffusion and sd 1. * relax tol for cycle diffusion 🚲 * relax tol for sd 1.0 * relax tol for controlnet. * determinism to img var. * relax tol for img variation. * tolerance to i2i sd * make style * determinism to inpaint. * relax tolerance for inpaiting. * determinism for inpainting legacy * relax tolerance. * determinism to instruct pix2pix * determinism to model editing. * model editing tolerance. * panorama determinism * determinism to pix2pix zero. * determinism to sag. * sd 2. determinism * sd. tolerance * disallow tf32 matmul. * relax tolerance is all you need. * make style and determinism to sd 2 depth * relax tolerance for depth. * tolerance to diffedit. * tolerance to sd 2 inpaint. * up tolerance. * determinism in upscaling. * tolerance in upscaler. * more tolerance relaxation. * determinism to v pred. * up tol for v_pred * unclip determinism * determinism to unclip img2img * determinism to text to video. * determinism to last set of tests * up tol. * vq cumsum doesn't have a deterministic kernel * relax tol * relax tol

add transformers to install

* [deepspeed] partial ZeRO-3 support * cleanup * improve deepspeed fixes * Improve * make style --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Add omegaconfg

…ace#3353) * Improve checkpointing lora * fix more * Improve doc string * Update src/diffusers/loaders.py * make stytle * Apply suggestions from code review * Update src/diffusers/loaders.py * Apply suggestions from code review * Apply suggestions from code review * better * Fix all * Fix multi-GPU dreambooth * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Fix all * make style * make style --------- Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* up * up

…ers (huggingface#3399) * Add `sigmoid` beta scheduler to `DDPMScheduler` docstring * Add `sigmoid` beta scheduler to `RePaintScheduler` docstring --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update pr_tests.yml

@patrickvonplaten

* Replace `AttentionBlock` with `Attention` * use _from_deprecated_attn_block check re: @patrickvonplaten

…ngface#3370) * add: benchmarking stats for A100 and V100. * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * address patrick's comments. * add: rtx 4090 stats * ⚔ benchmark reports done * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * 3313 pr link. * add: plots. Co-authored-by: Pedro <pedro@huggingface.co> * fix formattimg * update number percent. --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Fix style rendering. * Fix typo

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add stable diffusion tensorrt img2img pipeline Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * update docstrings Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> --------- Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* refactor controlnet and add img2img and inpaint * First draft to get pipelines to work * make style * Fix more * Fix more * More tests * Fix more * Make inpainting work * make style and more tests * Apply suggestions from code review * up * make style * Fix imports * Fix more * Fix more * Improve examples * add test * Make sure import is correctly deprecated * Make sure everything works in compile mode * make sure authorship is correctly attributed

* Add DPM-Solver Multistep Inverse Scheduler * Add draft tests for DiffEdit * Add inverse sde-dpmsolver steps to tune image diversity from inverted latents * Fix tests --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Fix incomplete docstrings for resnet.py

fix tiled vae bleand extent range

Small update to "Next steps" section: - PyTorch 2 is recommended. - Updated improvement figures.

…e#3298) * Update pipeline_if_superresolution.py Allow arbitrary aspect ratio in IFSuperResolutionPipeline by using the input image shape * IFSuperResolutionPipeline: allow the user to override the height and width through the arguments * update IFSuperResolutionPipeline width/height doc string to match StableDiffusionInpaintPipeline conventions --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

…gingface#3424) * Added explanation of 'strength' parameter * Added get_timesteps function which relies on new strength parameter * Added `strength` parameter which defaults to 1. * Swapped ordering so `noise_timestep` can be calculated before masking the image this is required when you aren't applying 100% noise to the masked region, e.g. strength < 1. * Added strength to check_inputs, throws error if out of range * Changed `prepare_latents` to initialise latents w.r.t strength inspired from the stable diffusion img2img pipeline, init latents are initialised by converting the init image into a VAE latent and adding noise (based upon the strength parameter passed in), e.g. random when strength = 1, or the init image at strength = 0. * WIP: Added a unit test for the new strength parameter in the StableDiffusionInpaintingPipeline still need to add correct regression values * Created a is_strength_max to initialise from pure random noise * Updated unit tests w.r.t new strength parameter + fixed new strength unit test * renamed parameter to avoid confusion with variable of same name * Updated regression values for new strength test - now passes * removed 'copied from' comment as this method is now different and divergent from the cpy * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Ensure backwards compatibility for prepare_mask_and_masked_image created a return_image boolean and initialised to false * Ensure backwards compatibility for prepare_latents * Fixed copy check typo * Fixes w.r.t backward compibility changes * make style * keep function argument ordering same for backwards compatibility in callees with copied from statements * make fix-copies --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: William Berman <WLBberman@gmail.com>

…s partially downloaded (huggingface#3448) Added bugfix using f strings.

…grad=False) (huggingface#3404) * gradient checkpointing bug fix * bug fix; changes for reviews * reformat * reformat --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Make dreambooth lora more robust to orig unet * up

…y're unnecessary) (huggingface#3463) Release large tensors in attention (as soon as they're no longer required). Reduces peak VRAM by nearly 2 GB for 1024x1024 (even after slicing), and the savings scale up with image size.

add min snr to text2img lora training script

* add inpaint lora scale support * add inpaint lora scale test --------- Co-authored-by: yueyang.hyy <yueyang.hyy@alibaba-inc.com>

* Correct from_ckpt * make style

…ngface#3478)

* dreambooth docs torch.compile note * Update examples/dreambooth/README.md Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * Update examples/dreambooth/README.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* add textual inversion inference to docs * add to toctree --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* distributed inference * move to inference section * apply feedback * update with split_between_processes * apply feedback

…lattened indices (huggingface#3479) explicit view kernel size as number elements in flattened indices

* Remove ONNX tests from PR. They are already a part of push_tests.yml. * Remove mps tests from PRs. They are already performed on push. * Fix workflow name for fast push tests. * Extract mps tests to a workflow. For better control/filtering. * Remove --extra-index-url from mps tests * Increase tolerance of mps test This test passes in my Mac (Ventura 13.3) but fails in the CI hardware (Ventura 13.2). I ran the local tests following the same steps that exist in the CI workflow. * Temporarily run mps tests on pr So we can test. * Revert "Temporarily run mps tests on pr" Tests passed, go back to running on push.

…ocessor2_0` (huggingface#3457) * add: debugging to enabling memory efficient processing * add: better warning message.

add note on local directory path. Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* up * fix more * Apply suggestions from code review * fix more * fix more * Check it * Remove 16:8 * fix more * fix more * fix more * up * up * Test only stable diffusion * Test only two files * up * Try out spinning up processes that can be killed * up * Apply suggestions from code review * up * up

* Fix DPM single * add test * fix one more bug * Apply suggestions from code review Co-authored-by: StAlKeR7779 <stalkek7779@yandex.ru> --------- Co-authored-by: StAlKeR7779 <stalkek7779@yandex.ru>

…3476) * add use_karras_sigmas * add karras test * add doc

…ngface#3486)

* feat) optimization kr translation * fix) typo, italic setting * feat) dreambooth, text2image kr * feat) lora kr * fix) LoRA * fix) fp16 fix * fix) doc-builder style * fix) fp16 일부 단어 수정 * fix) fp16 style fix * fix) opt, training docs update * feat) toctree update * feat) toctree update --------- Co-authored-by: Chanran Kim <seriousran@gmail.com>

* DataLoader will now bake in any transforms or image manipulations contained in the EXIF Images may have rotations stored in EXIF. Training using such images will cause those transforms to be ignored while training and thus produce unexpected results * Fixed the Dataloading EXIF issue in main DreamBooth training as well * Run make style (black & isort)

@patrickvonplaten

* allow disk offload for diffuser models * sort import * add max_memory argument * Changed sample[0] to images[0] (huggingface#3304) A pipeline object stores the results in `images` not in `sample`. Current code blocks don't work. * Typo in tutorial (huggingface#3295) * Torch compile graph fix (huggingface#3286) * fix more * Fix more * fix more * Apply suggestions from code review * fix * make style * make fix-copies * fix * make sure torch compile * Clean * fix test * Postprocessing refactor img2img (huggingface#3268) * refactor img2img VaeImageProcessor.postprocess * remove copy from for init, run_safety_checker, decode_latents Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> --------- Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * [Torch 2.0 compile] Fix more torch compile breaks (huggingface#3313) * Fix more torch compile breaks * add tests * Fix all * fix controlnet * fix more * Add Horace He as co-author. > > Co-authored-by: Horace He <horacehe2007@yahoo.com> * Add Horace He as co-author. Co-authored-by: Horace He <horacehe2007@yahoo.com> --------- Co-authored-by: Horace He <horacehe2007@yahoo.com> * fix: scale_lr and sync example readme and docs. (huggingface#3299) * fix: scale_lr and sync example readme and docs. * fix doc link. * Update stable_diffusion.mdx (huggingface#3310) fixed import statement * Fix missing variable assign in DeepFloyd-IF-II (huggingface#3315) Fix missing variable assign lol * Correct doc build for patch releases (huggingface#3316) Update build_documentation.yml * Add Stable Diffusion RePaint to community pipelines (huggingface#3320) * Add Stable Diffsuion RePaint to community pipelines - Adds Stable Diffsuion RePaint to community pipelines - Add Readme enty for pipeline * Fix: Remove wrong import - Remove wrong import - Minor change in comments * Fix: Code formatting of stable_diffusion_repaint * Fix: ruff errors in stable_diffusion_repaint * Fix multistep dpmsolver for cosine schedule (suitable for deepfloyd-if) (huggingface#3314) * fix multistep dpmsolver for cosine schedule (deepfloy-if) * fix a typo * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update src/diffusers/schedulers/scheduling_dpmsolver_multistep.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * update all dpmsolver (singlestep, multistep, dpm, dpm++) for cosine noise schedule * add test, fix style --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * [docs] Improve LoRA docs (huggingface#3311) * update docs * add to toctree * apply feedback * Added input pretubation (huggingface#3292) * Added input pretubation * Fixed spelling * Update write_own_pipeline.mdx (huggingface#3323) * update controlling generation doc with latest goodies. (huggingface#3321) * [Quality] Make style (huggingface#3341) * Fix config dpm (huggingface#3343) * Add the SDE variant of DPM-Solver and DPM-Solver++ (huggingface#3344) * add SDE variant of DPM-Solver and DPM-Solver++ * add test * fix typo * fix typo * Add upsample_size to AttnUpBlock2D, AttnDownBlock2D (huggingface#3275) The argument `upsample_size` needs to be added to these modules to allow compatibility with other blocks that require this argument. * Rename --only_save_embeds to --save_as_full_pipeline (huggingface#3206) * Set --only_save_embeds to False by default Due to how the option is named, it makes more sense to behave like this. * Refactor only_save_embeds to save_as_full_pipeline * [AudioLDM] Generalise conversion script (huggingface#3328) Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Fix TypeError when using prompt_embeds and negative_prompt (huggingface#2982) * test: Added test case * fix: fixed type checking issue on _encode_prompt * fix: fixed copies consistency * fix: one copy was not sufficient * Fix pipeline class on README (huggingface#3345) Update README.md * Inpainting: typo in docs (huggingface#3331) Typo in docs Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Add `use_Karras_sigmas` to LMSDiscreteScheduler (huggingface#3351) * add karras sigma to lms discrete scheduler * add test for lms_scheduler karras * reformat test lms * Batched load of textual inversions (huggingface#3277) * Batched load of textual inversions - Only call resize_token_embeddings once per batch as it is the most expensive operation - Allow pretrained_model_name_or_path and token to be an optional list - Remove Dict from type annotation pretrained_model_name_or_path as it was not supported in this function - Add comment that single files (e.g. .pt/.safetensors) are supported - Add comment for token parameter - Convert token override log message from warning to info * Update src/diffusers/loaders.py Check for duplicate tokens Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update condition for None tokens --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * make fix-copies * [docs] Fix docstring (huggingface#3334) fix docstring Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * if dreambooth lora (huggingface#3360) * update IF stage I pipelines add fixed variance schedulers and lora loading * added kv lora attn processor * allow loading into alternative lora attn processor * make vae optional * throw away predicted variance * allow loading into added kv lora layer * allow load T5 * allow pre compute text embeddings * set new variance type in schedulers * fix copies * refactor all prompt embedding code class prompts are now included in pre-encoding code max tokenizer length is now configurable embedding attention mask is now configurable * fix for when variance type is not defined on scheduler * do not pre compute validation prompt if not present * add example test for if lora dreambooth * add check for train text encoder and pre compute text embeddings * Postprocessing refactor all others (huggingface#3337) * add text2img * fix-copies * add * add all other pipelines * add * add * add * add * add * make style * style + fix copies --------- Co-authored-by: yiyixuxu <yixu310@gmail,com> * [docs] Improve safetensors docstring (huggingface#3368) * clarify safetensor docstring * fix typo * apply feedback * add: a warning message when using xformers in a PT 2.0 env. (huggingface#3365) * add: a warning message when using xformers in a PT 2.0 env. * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * StableDiffusionInpaintingPipeline - resize image w.r.t height and width (huggingface#3322) * StableDiffusionInpaintingPipeline now resizes input images and masks w.r.t to passed input height and width. Default is already set to 512. This addresses the common tensor mismatch error. Also moved type check into relevant funciton to keep main pipeline body tidy. * Fixed StableDiffusionInpaintingPrepareMaskAndMaskedImageTests Due to previous commit these tests were failing as height and width need to be passed into the prepare_mask_and_masked_image function, I have updated the code and added a height/width variable per unit test as it seemed more appropriate than the current hard coded solution * Added a resolution test to StableDiffusionInpaintPipelineSlowTests this unit test simply gets the input and resizes it into some that would fail (e.g. would throw a tensor mismatch error/not a mult of 8). Then passes it through the pipeline and verifies it produces output with correct dims w.r.t the passed height and width --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * make style * [docs] Adapt a model (huggingface#3326) * first draft * apply feedback * conv_in.weight thrown away * [docs] Load safetensors (huggingface#3333) * safetensors * apply feedback * apply feedback * Apply suggestions from code review --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * make style * [Docs] Fix stable_diffusion.mdx typo (huggingface#3398) Fix typo in last code block. Correct "prommpts" to "prompt" * Support ControlNet v1.1 shuffle properly (huggingface#3340) * add inferring_controlnet_cond_batch * Revert "add inferring_controlnet_cond_batch" This reverts commit abe8d63. * set guess_mode to True whenever global_pool_conditions is True Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * nit * add integration test --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * [Tests] better determinism (huggingface#3374) * enable deterministic pytorch and cuda operations. * disable manual seeding. * make style && make quality for unet_2d tests. * enable determinism for the unet2dconditional model. * add CUBLAS_WORKSPACE_CONFIG for better reproducibility. * relax tolerance (very weird issue, though). * revert to torch manual_seed() where needed. * relax more tolerance. * better placement of the cuda variable and relax more tolerance. * enable determinism for 3d condition model. * relax tolerance. * add: determinism to alt_diffusion. * relax tolerance for alt diffusion. * dance diffusion. * dance diffusion is flaky. * test_dict_tuple_outputs_equivalent edit. * fix two more tests. * fix more ddim tests. * fix: argument. * change to diff in place of difference. * fix: test_save_load call. * test_save_load_float16 call. * fix: expected_max_diff * fix: paint by example. * relax tolerance. * add determinism to 1d unet model. * torch 2.0 regressions seem to be brutal * determinism to vae. * add reason to skipping. * up tolerance. * determinism to vq. * determinism to cuda. * determinism to the generic test pipeline file. * refactor general pipelines testing a bit. * determinism to alt diffusion i2i * up tolerance for alt diff i2i and audio diff * up tolerance. * determinism to audioldm * increase tolerance for audioldm lms. * increase tolerance for paint by paint. * increase tolerance for repaint. * determinism to cycle diffusion and sd 1. * relax tol for cycle diffusion 🚲 * relax tol for sd 1.0 * relax tol for controlnet. * determinism to img var. * relax tol for img variation. * tolerance to i2i sd * make style * determinism to inpaint. * relax tolerance for inpaiting. * determinism for inpainting legacy * relax tolerance. * determinism to instruct pix2pix * determinism to model editing. * model editing tolerance. * panorama determinism * determinism to pix2pix zero. * determinism to sag. * sd 2. determinism * sd. tolerance * disallow tf32 matmul. * relax tolerance is all you need. * make style and determinism to sd 2 depth * relax tolerance for depth. * tolerance to diffedit. * tolerance to sd 2 inpaint. * up tolerance. * determinism in upscaling. * tolerance in upscaler. * more tolerance relaxation. * determinism to v pred. * up tol for v_pred * unclip determinism * determinism to unclip img2img * determinism to text to video. * determinism to last set of tests * up tol. * vq cumsum doesn't have a deterministic kernel * relax tol * relax tol * [docs] Add transformers to install (huggingface#3388) add transformers to install * [deepspeed] partial ZeRO-3 support (huggingface#3076) * [deepspeed] partial ZeRO-3 support * cleanup * improve deepspeed fixes * Improve * make style --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Add omegaconf for tests (huggingface#3400) Add omegaconfg * Fix various bugs with LoRA Dreambooth and Dreambooth script (huggingface#3353) * Improve checkpointing lora * fix more * Improve doc string * Update src/diffusers/loaders.py * make stytle * Apply suggestions from code review * Update src/diffusers/loaders.py * Apply suggestions from code review * Apply suggestions from code review * better * Fix all * Fix multi-GPU dreambooth * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Fix all * make style * make style --------- Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Fix docker file (huggingface#3402) * up * up * fix: deepseepd_plugin retrieval from accelerate state (huggingface#3410) * [Docs] Add `sigmoid` beta_scheduler to docstrings of relevant Schedulers (huggingface#3399) * Add `sigmoid` beta scheduler to `DDPMScheduler` docstring * Add `sigmoid` beta scheduler to `RePaintScheduler` docstring --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Don't install accelerate and transformers from source (huggingface#3415) * Don't install transformers and accelerate from source (huggingface#3414) * Improve fast tests (huggingface#3416) Update pr_tests.yml * attention refactor: the trilogy (huggingface#3387) * Replace `AttentionBlock` with `Attention` * use _from_deprecated_attn_block check re: @patrickvonplaten * [Docs] update the PT 2.0 optimization doc with latest findings (huggingface#3370) * add: benchmarking stats for A100 and V100. * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * address patrick's comments. * add: rtx 4090 stats * ⚔ benchmark reports done * Apply suggestions from code review Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * 3313 pr link. * add: plots. Co-authored-by: Pedro <pedro@huggingface.co> * fix formattimg * update number percent. --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Fix style rendering (huggingface#3433) * Fix style rendering. * Fix typo * unCLIP scheduler do not use note (huggingface#3417) * Replace deprecated command with environment file (huggingface#3409) Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * fix warning message pipeline loading (huggingface#3446) * add stable diffusion tensorrt img2img pipeline (huggingface#3419) * add stable diffusion tensorrt img2img pipeline Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * update docstrings Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> --------- Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * Refactor controlnet and add img2img and inpaint (huggingface#3386) * refactor controlnet and add img2img and inpaint * First draft to get pipelines to work * make style * Fix more * Fix more * More tests * Fix more * Make inpainting work * make style and more tests * Apply suggestions from code review * up * make style * Fix imports * Fix more * Fix more * Improve examples * add test * Make sure import is correctly deprecated * Make sure everything works in compile mode * make sure authorship is correctly attributed * [Scheduler] DPM-Solver (++) Inverse Scheduler (huggingface#3335) * Add DPM-Solver Multistep Inverse Scheduler * Add draft tests for DiffEdit * Add inverse sde-dpmsolver steps to tune image diversity from inverted latents * Fix tests --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * [Docs] Fix incomplete docstring for resnet.py (huggingface#3438) Fix incomplete docstrings for resnet.py * fix tiled vae blend extent range (huggingface#3384) fix tiled vae bleand extent range * Small update to "Next steps" section (huggingface#3443) Small update to "Next steps" section: - PyTorch 2 is recommended. - Updated improvement figures. * Allow arbitrary aspect ratio in IFSuperResolutionPipeline (huggingface#3298) * Update pipeline_if_superresolution.py Allow arbitrary aspect ratio in IFSuperResolutionPipeline by using the input image shape * IFSuperResolutionPipeline: allow the user to override the height and width through the arguments * update IFSuperResolutionPipeline width/height doc string to match StableDiffusionInpaintPipeline conventions --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Adding 'strength' parameter to StableDiffusionInpaintingPipeline (huggingface#3424) * Added explanation of 'strength' parameter * Added get_timesteps function which relies on new strength parameter * Added `strength` parameter which defaults to 1. * Swapped ordering so `noise_timestep` can be calculated before masking the image this is required when you aren't applying 100% noise to the masked region, e.g. strength < 1. * Added strength to check_inputs, throws error if out of range * Changed `prepare_latents` to initialise latents w.r.t strength inspired from the stable diffusion img2img pipeline, init latents are initialised by converting the init image into a VAE latent and adding noise (based upon the strength parameter passed in), e.g. random when strength = 1, or the init image at strength = 0. * WIP: Added a unit test for the new strength parameter in the StableDiffusionInpaintingPipeline still need to add correct regression values * Created a is_strength_max to initialise from pure random noise * Updated unit tests w.r.t new strength parameter + fixed new strength unit test * renamed parameter to avoid confusion with variable of same name * Updated regression values for new strength test - now passes * removed 'copied from' comment as this method is now different and divergent from the cpy * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Ensure backwards compatibility for prepare_mask_and_masked_image created a return_image boolean and initialised to false * Ensure backwards compatibility for prepare_latents * Fixed copy check typo * Fixes w.r.t backward compibility changes * make style * keep function argument ordering same for backwards compatibility in callees with copied from statements * make fix-copies --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: William Berman <WLBberman@gmail.com> * [WIP] Bugfix - Pipeline.from_pretrained is broken when the pipeline is partially downloaded (huggingface#3448) Added bugfix using f strings. * Fix gradient checkpointing bugs in freezing part of models (requires_grad=False) (huggingface#3404) * gradient checkpointing bug fix * bug fix; changes for reviews * reformat * reformat --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Make dreambooth lora more robust to orig unet (huggingface#3462) * Make dreambooth lora more robust to orig unet * up * Reduce peak VRAM by releasing large attention tensors (as soon as they're unnecessary) (huggingface#3463) Release large tensors in attention (as soon as they're no longer required). Reduces peak VRAM by nearly 2 GB for 1024x1024 (even after slicing), and the savings scale up with image size. * Add min snr to text2img lora training script (huggingface#3459) add min snr to text2img lora training script * Add inpaint lora scale support (huggingface#3460) * add inpaint lora scale support * add inpaint lora scale test --------- Co-authored-by: yueyang.hyy <yueyang.hyy@alibaba-inc.com> * [From ckpt] Fix from_ckpt (huggingface#3466) * Correct from_ckpt * make style * Update full dreambooth script to work with IF (huggingface#3425) * Add IF dreambooth docs (huggingface#3470) * parameterize pass single args through tuple (huggingface#3477) * attend and excite tests disable determinism on the class level (huggingface#3478) * dreambooth docs torch.compile note (huggingface#3471) * dreambooth docs torch.compile note * Update examples/dreambooth/README.md Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * Update examples/dreambooth/README.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * add: if entry in the dreambooth training docs. (huggingface#3472) * [docs] Textual inversion inference (huggingface#3473) * add textual inversion inference to docs * add to toctree --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * [docs] Distributed inference (huggingface#3376) * distributed inference * move to inference section * apply feedback * update with split_between_processes * apply feedback * [{Up,Down}sample1d] explicit view kernel size as number elements in flattened indices (huggingface#3479) explicit view kernel size as number elements in flattened indices * mps & onnx tests rework (huggingface#3449) * Remove ONNX tests from PR. They are already a part of push_tests.yml. * Remove mps tests from PRs. They are already performed on push. * Fix workflow name for fast push tests. * Extract mps tests to a workflow. For better control/filtering. * Remove --extra-index-url from mps tests * Increase tolerance of mps test This test passes in my Mac (Ventura 13.3) but fails in the CI hardware (Ventura 13.2). I ran the local tests following the same steps that exist in the CI workflow. * Temporarily run mps tests on pr So we can test. * Revert "Temporarily run mps tests on pr" Tests passed, go back to running on push. --------- Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> Co-authored-by: Ilia Larchenko <41329713+IliaLarchenko@users.noreply.github.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: YiYi Xu <yixu310@gmail.com> Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> Co-authored-by: Horace He <horacehe2007@yahoo.com> Co-authored-by: Umar <55330742+mu94-csl@users.noreply.github.com> Co-authored-by: Mylo <36931363+gitmylo@users.noreply.github.com> Co-authored-by: Markus Pobitzer <markuspobitzer@gmail.com> Co-authored-by: Cheng Lu <lucheng.lc15@gmail.com> Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> Co-authored-by: Isamu Isozaki <isamu.website@gmail.com> Co-authored-by: Cesar Aybar <csaybar@gmail.com> Co-authored-by: Will Rice <will@spokestack.io> Co-authored-by: Adrià Arrufat <1671644+arrufat@users.noreply.github.com> Co-authored-by: Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com> Co-authored-by: At-sushi <dkahw210@kyoto.zaq.ne.jp> Co-authored-by: Lucca Zenóbio <luccazen@gmail.com> Co-authored-by: Lysandre Debut <lysandre@huggingface.co> Co-authored-by: Isotr0py <41363108+Isotr0py@users.noreply.github.com> Co-authored-by: pdoane <pdoane2@gmail.com> Co-authored-by: Will Berman <wlbberman@gmail.com> Co-authored-by: yiyixuxu <yixu310@gmail,com> Co-authored-by: Rupert Menneer <71332436+rupertmenneer@users.noreply.github.com> Co-authored-by: sudowind <wfpkueecs@163.com> Co-authored-by: Takuma Mori <takuma104@gmail.com> Co-authored-by: Stas Bekman <stas00@users.noreply.github.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> Co-authored-by: Laureηt <laurentfainsin@protonmail.com> Co-authored-by: Jongwoo Han <jongwooo.han@gmail.com> Co-authored-by: asfiyab-nvidia <117682710+asfiyab-nvidia@users.noreply.github.com> Co-authored-by: clarencechen <clarencechenct@gmail.com> Co-authored-by: Laureηt <laurent@fainsin.bzh> Co-authored-by: superlabs-dev <133080491+superlabs-dev@users.noreply.github.com> Co-authored-by: Dev Aggarwal <devxpy@gmail.com> Co-authored-by: Vimarsh Chaturvedi <vimarsh.c@gmail.com> Co-authored-by: 7eu7d7 <31194890+7eu7d7@users.noreply.github.com> Co-authored-by: cmdr2 <shashank.shekhar.global@gmail.com> Co-authored-by: wfng92 <43742196+wfng92@users.noreply.github.com> Co-authored-by: Glaceon-Hyy <ffheyy0017@gmail.com> Co-authored-by: yueyang.hyy <yueyang.hyy@alibaba-inc.com>

* add reference only control * add reference only control * add reference only control * fix lint * fix lint * reference adain * bugfix EulerAncestralDiscreteScheduler * fix style fidelity rule * fix default output size * del unused line * fix deterministic

* Cross-attention masks prefer qualified symbol, fix accidental Optional prefer qualified symbol in AttentionProcessor prefer qualified symbol in embeddings.py qualified symbol in transformed_2d qualify FloatTensor in unet_2d_blocks move new transformer_2d params attention_mask, encoder_attention_mask to the end of the section which is assumed (e.g. by functions such as checkpoint()) to have a stable positional param interface. regard return_dict as a special-case which is assumed to be injected separately from positional params (e.g. by create_custom_forward()). move new encoder_attention_mask param to end of CrossAttn block interfaces and Unet2DCondition interface, to maintain positional param interface. regenerate modeling_text_unet.py remove unused import unet_2d_condition encoder_attention_mask docs Co-authored-by: Pedro Cuenca <pedro@huggingface.co> versatile_diffusion/modeling_text_unet.py encoder_attention_mask docs Co-authored-by: Pedro Cuenca <pedro@huggingface.co> transformer_2d encoder_attention_mask docs Co-authored-by: Pedro Cuenca <pedro@huggingface.co> unet_2d_blocks.py: add parameter name comments Co-authored-by: Pedro Cuenca <pedro@huggingface.co> revert description. bool-to-bias treatment happens in unet_2d_condition only. comment parameter names fix copies, style * encoder_attention_mask for SimpleCrossAttnDownBlock2D, SimpleCrossAttnUpBlock2D * encoder_attention_mask for UNetMidBlock2DSimpleCrossAttn * support attention_mask, encoder_attention_mask in KCrossAttnDownBlock2D, KCrossAttnUpBlock2D, KAttentionBlock. fix binding of attention_mask, cross_attention_kwargs params in KCrossAttnDownBlock2D, KCrossAttnUpBlock2D checkpoint invocations. * fix mistake made during merge conflict resolution * regenerate versatile_diffusion * pass time embedding into checkpointed attention invocation * always assume encoder_attention_mask is a mask (i.e. not a bias). * style, fix-copies * add tests for cross-attention masks * add test for padding of attention mask * explain mask's query_tokens dim. fix explanation about broadcasting over channels; we actually broadcast over query tokens * support both masks and biases in Transformer2DModel#forward. document behaviour * fix-copies * delete attention_mask docs on the basis I never tested self-attention masking myself. not comfortable explaining it, since I don't actually understand how a self-attn mask can work in its current form: the key length will be different in every ResBlock (we don't downsample the mask when we downsample the image). * review feedback: the standard Unet blocks shouldn't pass temb to attn (only to resnet). remove from KCrossAttnDownBlock2D,KCrossAttnUpBlock2D#forward. * remove encoder_attention_mask param from SimpleCrossAttn{Up,Down}Block2D,UNetMidBlock2DSimpleCrossAttn, and mask-choice in those blocks' #forward, on the basis that they only do one type of attention, so the consumer can pass whichever type of attention_mask is appropriate. * put attention mask padding back to how it was (since the SD use-case it enabled wasn't important, and it breaks the original unclip use-case). disable the test which was added. * fix-copies * style * fix-copies * put encoder_attention_mask param back into Simple block forward interfaces, to ensure consistency of forward interface. * restore passing of emb to KAttentionBlock#forward, on the basis that removal caused test failures. restore also the passing of emb to checkpointed calls to KAttentionBlock#forward. * make simple unet2d blocks use encoder_attention_mask, but only when attention_mask is None. this should fix UnCLIP compatibility. * fix copies

…hen loading from checkpoint (huggingface#3506)

This reverts commit ec7fb87.

* Batched load of textual inversions - Only call resize_token_embeddings once per batch as it is the most expensive operation - Allow pretrained_model_name_or_path and token to be an optional list - Remove Dict from type annotation pretrained_model_name_or_path as it was not supported in this function - Add comment that single files (e.g. .pt/.safetensors) are supported - Add comment for token parameter - Convert token override log message from warning to info * Update src/diffusers/loaders.py Check for duplicate tokens Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Update condition for None tokens --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

This reverts commit 302fde9.

…to remove CPU specific logic.

- Updated the checkpoint ids to the new ids where appropriate - Refactored the UniDiffuserTextDecoder methods to return only tensors (and made other changes to support this) - Cleaned up the code following suggestions by patrickvonplaten

…the inputs are already padded to a consistent length.

…ing/unidiffuser-test-v1.

…fuser.mdx to /api/diffusion_pipeline.mdx.

Commits on May 22, 2023

Revert bad commit and clean up code.

dg845 committed May 22, 2023

Configuration menu

View commit details

Copy full SHA for 9f7247c

Browse repository at this point

Copy the full SHA

9f7247c View commit details

Browse the repository at this point in the history

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add UniDiffuser model and pipeline #2963

Add UniDiffuser model and pipeline #2963

Commits on May 5, 2023

Commits on May 6, 2023

Commits on May 9, 2023

Commits on May 11, 2023

Commits on May 12, 2023

Commits on May 15, 2023

Commits on May 16, 2023

Commits on May 17, 2023

Commits on May 21, 2023

Commits on May 22, 2023

Commits on May 23, 2023

Commits on May 24, 2023

Commits on May 25, 2023

Commits on May 26, 2023