GitLab

* StableDiffusion: Decode latents separately to run larger batches

* Move VAE sliced decode under enable_vae_sliced_decode and vae.enable_sliced_decode

* Rename sliced_decode to slicing

* fix whitespace

* fix quality check and repository consistency

* VAE slicing tests and documentation

* API doc hooks for VAE slicing

* reformat vae slicing tests

* Skip VAE slicing for one-image batches

* Documentation tweaks for VAE slicing
Co-authored-by: Ilmari Heikkinen <ilmari@fhtr.org>

* Flax: start adapting to Stable Diffusion 2

* More changes.

* attention_head_dim can be a tuple.

* Fix typos

* Add simple SD 2 integration test.

Slice values taken from my Ampere GPU.

* Add simple UNet integration tests for Flax.

Note that the expected values are taken from the PyTorch results. This
ensures the Flax and PyTorch versions are not too far off.

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

* Typos and style

* Tests: verify jax is available.

* Style

* Make flake happy

* Remove typo.

* Simple Flax SD 2 pipeline tests.

* Import order

* Remove unused import.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: @camenduru 

* Add heun

* Finish first version of heun

* remove bogus

* finish

* finish

* improve

* up

* up

* fix more

* change progress bar

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

* finish

* up

* up

* up

* Ensure Flax pipeline always returns numpy array.

* Clarify documentation.

Fix Flax `from_pt`.

It worked for models but not for pipelines.
Accidentally broken in #1107.

* add get_velocity

* add v prediction for training

* fix saving

* add revision arg

* fix saving

* save checkpoints dreambooth

* fix saving embeds

* add instruction in readme

* quality

* noise_pred -> model_pred

Remove kwargs from call

* [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>

* added initial v-pred support to DPM-solver

* fix sign

* added v_prediction to flax

* fixed typo

* StableDiffusionUpscalePipeline

* fix a few things

* make it better

* fix image batching

* run vae in fp32

* fix docstr

* resize to mul of 64

* doc

* remove safety_checker

* add max_noise_level

* fix Copied

* begin tests

* slow tests

* default max_noise_level

* remove kwargs

* doc

* fix

* fix fast tests

* fix fast tests

* no sf

* don't offload vae
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* fix

* fix deprecated kwargs logic

* add tests

* finish

* Adapt ddpm, ddpmsolver to prediction_type.

* Deprecate predict_epsilon in __init__.

* Bring FlaxDDIMScheduler up to date with DDIMScheduler.

* Set prediction_type as an ivar for consistency.

* Convert pipeline_ddpm

* Adapt tests.

* Adapt unconditional training script.

* Adapt BitDiffusion example.

* Add missing kwargs in dpmsolver_multistep

* Ugly workaround to accept deprecated predict_epsilon when loading
schedulers using from_pretrained.

* make style

* Remove import no longer in use.

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

* Use config.prediction_type everywhere

* Add a couple of Flax prediction type tests.

* make style

* fix register deprecated arg
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* call contiguous after permute

Fixes for MPS device

* Fix MPS UserWarning

* make style

* Revert "Fix MPS UserWarning"

This reverts commit b46c32810ee5fdc4c16a8e9224a826490b66cf49.

fix all tests

* up

* uP

* Support SD2 attention slicing

* Support SD2 attention slicing

* Add more copies

* Use attn_num_head_channels in blocks

* fix-copies

* Update tests

* fix imports

* up

* up

* fix

* uP

* more fixes

* up

* uP

* up

* up

* uP

* fix final tests

* Upscaling fixed

* up

* more fixes

* fix

* more fixes

* finish again

* up

* Optional Components

* uP

* finish

* finish

* finish

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

* up

* Update src/diffusers/pipeline_utils.py

* improve
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix

* add test

* fix test

* uP

* up

* fix some tests

* allow disabling self attention

* add class_embedding

* fix copies

* fix condition

* fix copies

* do_self_attention -> only_cross_attention

* fix copies

* num_classes -> num_class_embeds

* fix default value

* add v prediction

* adat euler for v pred

* velocity -> v_prediction

* simplify

* fix naming

* Update src/diffusers/schedulers/scheduling_euler_discrete.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* style
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix imports

* better error

* up

* finish

don't norm twice

* boom boom

* remove duplicate arg

* add use_linear_proj arg

* fix copies

* style

* add fast tests

* use_linear_proj -> use_linear_projection

* up

* convert dual unet

* revert dual attn

* adapt for vd-official

* test the full pipeline

* mixed inference

* mixed inference for text2img

* add image prompting

* fix clip norm

* split text2img and img2img

* fix format

* refactor text2img

* mega pipeline

* add optimus

* refactor image var

* wip text_unet

* text unet end to end

* update tests

* reshape

* fix image to text

* add some first docs

* dual guided pipeline

* fix token ratio

* propose change

* dual transformer as a native module

* DualTransformer(nn.Module)

* DualTransformer(nn.Module)

* correct unconditional image

* save-load with mega pipeline

* remove image to text

* up

* uP

* fix

* up

* final fix

* remove_unused_weights

* test updates

* save progress

* uP

* fix dual prompts

* some fixes

* finish

* style

* finish renaming

* up

* fix

* fix

* fix

* finish
Co-authored-by: anton-l <anton@huggingface.co>

* add StableDiffusionImageVariationPipeline

* add ini init

* use CLIPVisionModelWithProjection

* fix _encode_image

* add copied from

* fix copies

* add doc

* handle tensor in _encode_image

* add tests

* correct model_id

* remove copied from in enable_sequential_cpu_offload

* fix tests

* make slow tests pass

* update slow tests

* use temp model for now

* fix test_stable_diffusion_img_variation_intermediate_state

* fix test_stable_diffusion_img_variation_intermediate_state

* check for torch.Tensor

* quality

* fix name

* fix slow tests

* install transformers from source

* fix install

* fix install

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

* input_image -> image

* remove deprication warnings

* fix test_stable_diffusion_img_variation_multiple_images

* make flake happy
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* make sure fp16 runs well

* add fp16 test for superes

* Update src/diffusers/models/unet_2d.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* gen on cuda

* always run fast inferecne test on cpu

* run on cpu
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix non square images with UNet2DModel and DDIM/DDPM pipelines

* fix unet_2d `sample_size` docstring

* update pipeline tests for unet uncond
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* use memory_efficient_attention by default

* Update src/diffusers/models/attention.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>