GitLab

* [Local loading] Correct bug with local files only

* file not found error

* fix

* finish

* Support to load Kohya-ss style LoRA file format (without restrictions)
Co-Authored-By: Takuma Mori <takuma104@gmail.com>
Co-Authored-By: Sayak Paul <spsayakpaul@gmail.com>

* tmp: add sdxl to mlp_modules

---------
Co-authored-by: Takuma Mori <takuma104@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Allow low precision sd xl

* finish

* finish

* feat: initial draft for supporting text encoder lora finetuning for SDXL DreamBooth

* fix: variable assignments.

* add: autocast block.

* add debugging

* vae dtype hell

* fix: vae dtype hell.

* fix: vae dtype hell 3.

* clean up

* lora text encoder loader.

* fix: unwrapping models.

* add: tests.

* docs.

* handle unexpected keys.

* fix vae dtype in the final inference.

* fix scope problem.

* fix: save_model_card args.

* initialize: prefix to None.

* fix: dtype issues.

* apply gixes.

* debgging.

* debugging

* debugging

* debugging

* debugging

* debugging

* add: fast tests.

* pre-tokenize.

* address: will's comments.

* fix: loader and tests.

* fix: dataloader.

* simplify dataloader.

* length.

* simplification.

* make style && make quality

* simplify state_dict munging

* fix: tests.

* fix: state_dict packing.

* 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 AsymmetricAutoencoderKL

* fixed copies+dummy

* added script to convert original asymmetric vqgan

* added docs

* updated docs

* fixed style

* fixes, added tests

* update doc

* fixed doc

* fixed tests

* naming
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* naming
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* udpated code example

* updated doc

* comments fixes

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

* comments fixes

* added inpaint pipeline tests

* comment suggestion: delete method

* yet another fixes

---------
Co-authored-by: Ruslan Vorovchenko <r.vorovchenko@prequelapp.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Add controlnet from single file

* Updates

* make style

* finish

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* feat: add act_fn param to OutValueFunctionBlock

* feat: update unet1d tests to not use mish

* feat: add `mish` as the default activation function
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* feat: drop mish tests from unet1d

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

* add: test for testing unloading lora.

* add :reason to skipif.

* initial implementation of lora unload().

* apply styling.

* add: doc.

* change checkpoints.

* reinit generator

* finalize slow test.

* add fast test for unloading lora.

* refactor to support patching LoRA into T5

instantiate the lora linear layer on the same device as the regular linear layer

get lora rank from state dict

tests

fmt

can create lora layer in float32 even when rest of model is float16

fix loading model hook

remove load_lora_weights_ and T5 dispatching

remove Unet#attn_processors_state_dict

docstrings

* text encoder monkeypatch class method

* fix test

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

* add default to unet output to prevent it from being a required arg

* add unit test

* make style

* adjust unit test

* mark as fast test

* adjust assert statement in test

---------

Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
Co-authored-by: root <root@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>

* Improve memory text to video

* Apply suggestions from code review

* add test

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

* finish test setup

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

* relax tolerance slightly

* correct incorrect naming

* correct namingc

* correct more

* Apply suggestions from code review

* Fix more

* Correct more

* correct incorrect naming

* Update src/diffusers/models/controlnet.py

* Correct flax

* Correct renaming

* Correct blocks

* Fix more

* Correct more

* mkae style

* mkae style

* mkae style

* mkae style

* mkae style

* Fix flax

* mkae style

* rename

* rename

* rename attn head dim to attention_head_dim

* correct flax

* make style

* improve

* Correct more

* make style

* fix more

* mkae style

* Update src/diffusers/models/controlnet_flax.py

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

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

* relax tolerance slightly

* Add more tests

* upload readme

* upload readme

* Apply suggestions from code review

* Improve API Autoencoder KL

* finalize

* finalize tests

* finalize tests

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* up

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

relax tolerance slightly

* Add draft for lora text encoder scale

* Improve naming

* fix: training dreambooth lora script.

* Apply suggestions from code review

* Update examples/dreambooth/train_dreambooth_lora.py

* Apply suggestions from code review

* Apply suggestions from code review

* add lora mixin when fit

* add lora mixin when fit

* add lora mixin when fit

* fix more

* fix more

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* feat: add lora attention processor for pt 2.0.

* explicit context manager for SDPA.

* switch to flash attention

* make shapes compatible to work optimally with SDPA.

* fix: circular import problem.

* explicitly specify the flash attention kernel in sdpa

* fall back to efficient attention context manager.

* remove explicit dispatch.

* fix: removed processor.

* fix: remove optional from type annotation.

* feat: make changes regarding LoRAAttnProcessor2_0.

* remove confusing warning.

* formatting.

* relax tolerance for PT 2.0

* fix: loading message.

* remove unnecessary logging.

* add: entry to the docs.

* add: network_alpha argument.

* relax tolerance.

* merge undoable-monkeypatch

* remove TEXT_ENCODER_TARGET_MODULES, refactoring

* move create_lora_weight_file

* move activation dispatches into helper function

* tests

* add _convert_kohya_lora_to_diffusers

* make style

* add scaffold

* match result: unet attention only

* fix monkey-patch for text_encoder

* with CLIPAttention

While the terrible images are no longer produced,
the results do not match those from the hook ver.
This may be due to not setting the network_alpha value.

* add to support network_alpha

* generate diff image

* fix monkey-patch for text_encoder

* add test_text_encoder_lora_monkey_patch()

* verify that it's okay to release the attn_procs

* fix closure version

* add comment

* Revert "fix monkey-patch for text_encoder"

This reverts commit bb9c61e6faecc1935c9c4319c77065837655d616.

* Fix to reuse utility functions

* make LoRAAttnProcessor targets to self_attn

* fix LoRAAttnProcessor target

* make style

* fix split key

* Update src/diffusers/loaders.py

* remove TEXT_ENCODER_TARGET_MODULES loop

* add print memory usage

* remove test_kohya_loras_scaffold.py

* add: doc on LoRA civitai

* remove print statement and refactor in the doc.

* fix state_dict test for kohya-ss style lora

* Apply suggestions from code review
Co-authored-by: Takuma Mori <takuma104@gmail.com>

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

Fix to apply LoRAXFormersAttnProcessor instead of LoRAAttnProcessor when xFormers is enabled (#3556)

* fix to use LoRAXFormersAttnProcessor

* add test

* using new LoraLoaderMixin.save_lora_weights

* add test_lora_save_load_with_xformers

* Run ControlNet compile test in a separate subprocess

`torch.compile()` spawns several subprocesses and the GPU memory used
was not reclaimed after the test ran. This approach was taken from
`transformers`.

* Style

* Prepare a couple more compile tests to run in subprocess.

* Use require_torch_2 decorator.

* Test inpaint_compile in subprocess.

* Run img2img compile test in subprocess.

* Run stable diffusion compile test in subprocess.

* style

* Temporarily trigger on pr to test.

* Revert "Temporarily trigger on pr to test."

This reverts commit 82d76868ddf9cc634a9f14b2b0aef1d5433cd750.

* 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

* 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

* Replace `AttentionBlock` with `Attention`

* use _from_deprecated_attn_block check re: @patrickvonplaten

* 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

* Make sure attention works with Torch 2_0

* make style

* Fix more

* 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>

* 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>

* [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>

* inital commit for lora test cases

* help a bit with lora for 3d

* fixed lora tests

* replaced redundant code

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

* add only cross attention to simple attention blocks

* add test for only_cross_attention re: @patrickvonplaten

* mid_block_only_cross_attention better default

allow mid_block_only_cross_attention to default to
`only_cross_attention` when `only_cross_attention` is given
as a single boolean

* [Config] Fix config prints and save, load

* Only use potential nn.Modules for dtype and device

* Correct vae image processor

* make sure in_channels is not accessed directly

* make sure in channels is only accessed via config

* Make sure schedulers only access config attributes

* Make sure to access config in SAG

* Fix vae processor and make style

* add tests

* uP

* make style

* Fix more naming issues

* Final fix with vae config

* change more

speed up test