GitLab

* Add new text encoder

* add transformers depth

* More

* Correct conversion script

* Fix more

* Fix more

* Correct more

* correct text encoder

* Finish all

* proof that in works in run local xl

* clean up

* Get refiner to work

* Add red castle

* Fix batch size

* Improve pipelines more

* Finish text2image tests

* Add img2img test

* Fix more

* fix import

* Fix embeddings for classic models (#3888)

Fix embeddings for classic SD models.

* Allow multiple prompts to be passed to the refiner (#3895)

* finish more

* Apply suggestions from code review

* add watermarker

* Model offload (#3889)

* Model offload.

* Model offload for refiner / img2img

* Hardcode encoder offload on img2img vae encode

Saves some GPU RAM in img2img / refiner tasks so it remains below 8 GB.

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

* correct

* fix

* clean print

* Update install warning for `invisible-watermark`

* add: missing docstrings.

* fix and simplify the usage example in img2img.

* fix setup for watermarking.

* Revert "fix setup for watermarking."

This reverts commit 491bc9f5a640bbf46a97a8e52d6eff7e70eb8e4b.

* fix: watermarking setup.

* fix: op.

* run make fix-copies.

* make sure tests pass

* improve convert

* make tests pass

* make tests pass

* better error message

* fiinsh

* finish

* Fix final test

---------
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* [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>

* 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>

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

* update import onnxruntime package, enable onnxruntime-rocm and onnxruntime-training

* add ort_nightly_gpu

* initial TokenEncoder and ContinuousEncoder

* initial modules

* added ContinuousContextTransformer

* fix copy paste error

* use numpy for get_sequence_length

* initial terminal relative positional encodings

* fix weights keys

* fix assert

* cross attend style: concat encodings

* make style

* concat once

* fix formatting

* Initial SpectrogramPipeline

* fix input_tokens

* make style

* added mel output

* ignore weights for config

* move mel to numpy

* import pipeline

* fix class names and import

* moved models to models folder

* import ContinuousContextTransformer and SpectrogramDiffusionPipeline

* initial spec diffusion converstion script

* renamed config to t5config

* added weight loading

* use arguments instead of t5config

* broadcast noise time to batch dim

* fix call

* added scale_to_features

* fix weights

* transpose laynorm weight

* scale is a vector

* scale the query outputs

* added comment

* undo scaling

* undo depth_scaling

* inital get_extended_attention_mask

* attention_mask is none in self-attention

* cleanup

* manually invert attention

* nn.linear need bias=False

* added T5LayerFFCond

* remove to fix conflict

* make style and dummy

* remove unsed variables

* remove predict_epsilon

* Move accelerate to a soft-dependency (#1134)

* finish

* finish

* Update src/diffusers/modeling_utils.py

* Update src/diffusers/pipeline_utils.py
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* more fixes

* fix
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* fix order

* added initial midi to note token data pipeline

* added int to int tokenizer

* remove duplicate

* added logic for segments

* add melgan to pipeline

* move autoregressive gen into pipeline

* added note_representation_processor_chain

* fix dtypes

* remove immutabledict req

* initial doc

* use np.where

* require note_seq

* fix typo

* update dependency

* added note-seq to test

* added is_note_seq_available

* fix import

* added toc

* added example usage

* undo for now

* moved docs

* fix merge

* fix imports

* predict first segment

* avoid un-needed copy to and from cpu

* make style

* Copyright

* fix style

* add test and fix inference steps

* remove bogus files

* reorder models

* up

* remove transformers dependency

* make work with diffusers cross attention

* clean more

* remove @

* improve further

* up

* uP

* Apply suggestions from code review

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py

* loop over all tokens

* make style

* Added a section on the model

* fix formatting

* grammer

* formatting

* make fix-copies

* Update src/diffusers/pipelines/__init__.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/spectrogram_diffusion/pipeline_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* added callback ad optional ionnx

* do not squeeze batch dim

* clean up more

* upload

* convert jax to nnumpy

* make style

* fix warning

* make fix-copies

* fix warning

* add initial fast tests

* add initial pipeline_params

* eval mode due to dropout

* skip batch tests as pipeline runs on a single file

* make style

* fix relative path

* fix doc tests

* Update src/diffusers/models/t5_film_transformer.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/models/t5_film_transformer.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/en/api/pipelines/spectrogram_diffusion.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add MidiProcessor

* format

* fix org

* Apply suggestions from code review

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py

* make style

* pin protobuf to <4

* fix formatting

* white space

* tensorboard needs protobuf

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* [MS Text To Video} Add first text to video

* upload

* make first model example

* match unet3d params

* make sure weights are correcctly converted

* improve

* forward pass works, but diff result

* make forward work

* fix more

* finish

* refactor video output class.

* feat: add support for a video export utility.

* fix: opencv availability check.

* run make fix-copies.

* add: docs for the model components.

* add: standalone pipeline doc.

* edit docstring of the pipeline.

* add: right path to TransformerTempModel

* add: first set of tests.

* complete fast tests for text to video.

* fix bug

* up

* three fast tests failing.

* add: note on slow tests

* make work with all schedulers

* apply styling.

* add slow tests

* change file name

* update

* more correction

* more fixes

* finish

* up

* Apply suggestions from code review

* up

* finish

* make copies

* fix pipeline tests

* fix more tests

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* apply suggestions

* up

* revert

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* add docs

* correct

* finish

* Apply suggestions from code review
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* update deps table

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* enable_model_offload PoC

It's surprisingly more involved than expected, see comments in the PR.

* Rename final_offload_hook

* Invoke the vae forward hook manually.

* Completely remove decoder.

* Style

* apply_forward_hook decorator

* Rename method.

* Style

* Copy enable_model_cpu_offload

* Fix copies.

* Remove comment.

* Fix copies

* Missing import

* Fix doc-builder style.

* Merge main and fix again.

* Add docs

* Fix docs.

* Add a couple of tests.

* style

* add: support for BLIP generation.

* add: support for editing synthetic images.

* remove unnecessary comments.

* add inits and run make fix-copies.

* version change of diffusers.

* fix: condition for loading the captioner.

* default conditions_input_image to False.

* guidance_amount -> cross_attention_guidance_amount

* fix inputs to check_inputs()

* fix: attribute.

* fix: prepare_attention_mask() call.

* debugging.

* better placement of references.

* remove torch.no_grad() decorations.

* put torch.no_grad() context before the first denoising loop.

* detach() latents before decoding them.

* put deocding in a torch.no_grad() context.

* add reconstructed image for debugging.

* no_grad(0

* apply formatting.

* address one-off suggestions from the draft PR.

* back to torch.no_grad() and add more elaborate comments.

* refactor prepare_unet() per Patrick's suggestions.

* more elaborate description for .

* formatting.

* add docstrings to the methods specific to pix2pix zero.

* suspecting a redundant noise prediction.

* needed for gradient computation chain.

* less hacks.

* fix: attention mask handling within the processor.

* remove attention reference map computation.

* fix: cross attn args.

* fix: prcoessor.

* store attention maps.

* fix: attention processor.

* update docs and better treatment to xa args.

* update the final noise computation call.

* change xa args call.

* remove xa args option from the pipeline.

* add: docs.

* first test.

* fix: url call.

* fix: argument call.

* remove image conditioning for now.

* 🚨 add: fast tests.

* explicit placement of the xa attn weights.

* add: slow tests 🐢

* fix: tests.

* edited direction embedding should be on the same device as prompt_embeds.

* debugging message.

* debugging.

* add pix2pix zero pipeline for a non-deterministic test.

* debugging/

* remove debugging message.

* make caption generation _

* address comments (part I).

* address PR comments (part II)

* fix: DDPM test assertion.

* refactor doc.

* address PR comments (part III).

* fix: type annotation for the scheduler.

* apply styling.

* skip_mps and add note on embeddings in the docs.

* [Examples] Test all examples on CPU

* add

* correct

* Apply suggestions from code review

* convert __main__ to a function call and call it

* add missing type hint

* make style check pass

* move loading to src/diffusers
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Switch to huggingface_hub.ModelCard

* Remove modelcards dependency in favor of Jinja2

* [Lora] first upload

* add first lora version

* upload

* more

* first training

* up

* correct

* improve

* finish loaders and inference

* up

* up

* fix more

* up

* finish more

* finish more

* up

* up

* change year

* revert year change

* Change lines

* Add cloneofsimo as co-author.
Co-authored-by: Simo Ryu <cloneofsimo@gmail.com>

* finish

* fix docs

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* upload

* finish
Co-authored-by: Simo Ryu <cloneofsimo@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Check k-diffusion version is at least 0.0.12

* make style

* Transformers version req for UnCLIP

* add to the list

* Adapt to forced transformers version in some dependent libraries

* style

* Update __init__.py

* update requires_backends

* begin depth pipeline

* add depth estimation model

* fix prepare_depth_mask

* add a comment about autocast

* copied from, quality, cleanup

* begin tests

* handle tensors

* norm image tensor

* fix batch size

* fix tests

* fix enable_sequential_cpu_offload

* fix save load

* fix test_save_load_float16

* fix test_save_load_optional_components

* fix test_float16_inference

* fix test_cpu_offload_forward_pass

* fix test_dict_tuple_outputs_equivalent

* up

* fix fast tests

* fix test_stable_diffusion_img2img_multiple_init_images

* fix few more fast tests

* don't use device map for DPT

* fix test_stable_diffusion_pipeline_with_sequential_cpu_offloading

* accept external depth maps

* prepare_depth_mask -> prepare_depth_map

* fix file name

* fix file name

* quality

* check transformers version

* fix test names

* use skipif

* fix import

* add docs

* skip tests on mps

* correct version

* uP

* Update docs/source/api/pipelines/stable_diffusion_2.mdx

* fix fix-copies

* fix fix-copies
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: anton- <anton@huggingface.co>

* Fix PyCharm/VSCode static type checking for dummy objects

* Re-add dummies

* Fix AudioDiffusion imports

* fix import

* fix import

* Update utils/check_dummies.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update src/diffusers/utils/import_utils.py

* Update src/diffusers/__init__.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/__init__.py

* fix double import
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* uP

* uP

* add AudioDiffusionPipeline and LatentAudioDiffusionPipeline

* add docs to toc

* fix tests

* fix tests

* fix tests

* fix tests

* fix tests

* Update pr_tests.yml

Fix tests

* parent 499ff34b3edc3e0c506313ab48f21514d8f58b09
author teticio <teticio@gmail.com> 1668765652 +0000
committer teticio <teticio@gmail.com> 1669041721 +0000

parent 499ff34b3edc3e0c506313ab48f21514d8f58b09
author teticio <teticio@gmail.com> 1668765652 +0000
committer teticio <teticio@gmail.com> 1669041704 +0000

add colab notebook

[Flax] Fix loading scheduler from subfolder (#1319)

[FLAX] Fix loading scheduler from subfolder

Fix/Enable all schedulers for in-painting (#1331)

* inpaint fix k lms

* onnox as well

* up

Correct path to schedlure (#1322)

* [Examples] Correct path

* uP

Avoid nested fix-copies (#1332)

* Avoid nested `# Copied from` statements during `make fix-copies`

* style

Fix img2img speed with LMS-Discrete Scheduler (#896)

Casting `self.sigmas` into a different dtype (the one of original_samples) is not advisable. In my img2img pipeline this leads to a long running time in the  `integrate.quad` call later on- by long I mean more than 10x slower.
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

Fix the order of casts for onnx inpainting (#1338)

Legacy Inpainting Pipeline for Onnx Models (#1237)

* Add legacy inpainting pipeline compatibility for onnx

* remove commented out line

* Add onnx legacy inpainting test

* Fix slow decorators

* pep8 styling

* isort styling

* dummy object

* ordering consistency

* style

* docstring styles

* Refactor common prompt encoding pattern

* Update tests to permanent repository home

* support all available schedulers until ONNX IO binding is available
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* updated styling from PR suggested feedback
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

Jax infer support negative prompt (#1337)

* support negative prompts in sd jax pipeline

* pass batched neg_prompt

* only encode when negative prompt is None
Co-authored-by: Juan Acevedo <jfacevedo@google.com>

Update README.md: Minor change to Imagic code snippet, missing dir error (#1347)

Minor change to Imagic Readme

Missing dir causes an error when running the example code.

make style

change the sample model (#1352)

* Update alt_diffusion.mdx

* Update alt_diffusion.mdx

Add bit diffusion [WIP] (#971)

* Create bit_diffusion.py

Bit diffusion based on the paper, arXiv:2208.04202, Chen2022AnalogBG

* adding bit diffusion to new branch

ran tests

* tests

* tests

* tests

* tests

* removed test folders + added to README

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

* move Mel to module in pipeline construction, make librosa optional

* fix imports

* fix copy & paste error in comment

* fix style

* add missing register_to_config

* fix class docstrings

* fix class docstrings

* tweak docstrings

* tweak docstrings

* update slow test

* put trailing commas back

* respect alphabetical order

* remove LatentAudioDiffusion, make vqvae optional

* move Mel from models back to pipelines :-)

* allow loading of pretrained audiodiffusion models

* fix tests

* fix dummies

* remove reference to latent_audio_diffusion in docs

* unused import

* inherit from SchedulerMixin to make loadable

* Apply suggestions from code review

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

* Add `ort_nightly_directml` to the `onnxruntime` candidates

* style

* [Proposal] Support loading from safetensors if file is present.

* Style.

* Fix.

* Adding some test to check loading logic.

+ modify download logic to not download pytorch file if not necessary.

* Fixing the logic.

* Adressing comments.

* factor out into a function.

* Remove dead function.

* Typo.

* Extra fetch only if safetensors is there.

* 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>

* fix imports

* better error

* up

* finish

* finish

* finish

* Update src/diffusers/modeling_utils.py

* Update src/diffusers/pipeline_utils.py
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* more fixes

* fix
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* 2x speedup using memory efficient attention

* remove einops dependency

* Swap K, M in op instantiation

* Simplify code, remove unnecessary maybe_init call and function, remove unused self.scale parameter

* make xformers a soft dependency

* remove one-liner functions

* change one letter variable to appropriate names

* Remove Env variable dependency, remove MemoryEfficientCrossAttention class and use enable_xformers_memory_efficient_attention method

* Add memory efficient attention toggle to img2img and inpaint pipelines

* Clearer management of xformers' availability

* update optimizations markdown to add info about memory efficient attention

* add benchmarks for TITAN RTX

* More detailed explanation of how the mem eff benchmark were ran

* Removing autocast from optimization markdown

* import_utils: import torch only if is available
Co-authored-by: Nouamane Tazi <nouamane98@gmail.com>

* Fix pipelines user_agent, ignore CI requests

* fix circular import

* N/A versions

* N/A versions

* add accelerate to load models with smaller memory footprint

* remove low_cpu_mem_usage as it is reduntant

* move accelerate init weights context to modelling utils

* add test to ensure results are the same when loading with accelerate

* add tests to ensure ram usage gets lower when using accelerate

* move accelerate logic to single snippet under modelling utils and remove it from configuration utils

* format code using to pass quality check

* fix imports with isor

* add accelerate to test extra deps

* only import accelerate if device_map is set to auto

* move accelerate availability check to diffusers import utils

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

* Fix is_onnx_available

Fix: If user install onnxruntime-gpu, is_onnx_available() will return False.

* add more onnxruntime candidates

* Run `make style`
Co-authored-by: anton-l <anton@huggingface.co>

* initial export and design

* update imports

* custom prover, import fixes

* Update src/diffusers/onnx_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/onnx_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove push_to_hub

* Update src/diffusers/onnx_utils.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* remove torch_device

* numpify the rest of the pipeline

* torchify the safety checker

* revert tensor

* Code review suggestions + quality

* fix tests

* fix provider, add an end-to-end test

* style
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add is_<framework>_available, refactor import utils

* deps

* quality