GitLab

* Impl tae slicing and tiling

* add tae tiling test

* add parameterized test

* formatted code

* fix failed test

* style docs

* make safetensors default

* set default save method as safetensors

* update tests

* update to support saving safetensors

* update test to account for safetensors default

* update example tests to use safetensors

* update example to support safetensors

* update unet tests for safetensors

* fix failing loader tests

* fix qc issues

* fix pipeline tests

* fix example test

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* Support higher dimension LoRAs

* add: tests

* fix: assertion values.

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

* fixed

* add: tests

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

[Pipeline utils] feat: implement push_to_hub for standalone models, schedulers as well as pipelines (#4128)

* feat: implement push_to_hub for standalone models.

* address PR feedback.

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

* remove max_shard_size.

* add: support for scheduler push_to_hub

* enable push_to_hub support for flax schedulers.

* enable push_to_hub for pipelines.

* Apply suggestions from code review
Co-authored-by: Lucain <lucainp@gmail.com>

* reflect pr feedback.

* address another round of deedback.

* better handling of kwargs.

* add: tests

* Apply suggestions from code review
Co-authored-by: Lucain <lucainp@gmail.com>

* setting hub staging to False for now.

* incorporate staging test as a separate job.
Co-authored-by: ydshieh <2521628+ydshieh@users.noreply.github.com>

* fix: tokenizer loading.

* fix: json dumping.

* move is_staging_test to a better location.

* better treatment to tokens.

* define repo_id to better handle concurrency

* style

* explicitly set token

* Empty-Commit

* move SUER, TOKEN to test

* collate org_repo_id

* delete repo

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: ydshieh <2521628+ydshieh@users.noreply.github.com>

* [WIP] Remove code snippets containing `is_safetensors_available()`

* Modifying `import_utils.py`

* update pipeline tests for safetensor default

* fix test related to cached requests

* address import nits

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* correct

* correct blocks

* finish

* finish

* finish

* Apply suggestions from code review

* fix

* up

* up

* up

* Update examples/dreambooth/README_sdxl.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Apply suggestions from code review

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

* add: integration tests for SDXL LoRAs.

* change pipeline class.

* fix assertion values.

* print values again.

* let's see.

* let's see.

* let's see.

* finish

* add: model implementation of tiny autoencoder.

* add: inits.

* push the latest devs.

* add: conversion script and finish.

* add: scaling factor args.

* debugging

* fix denormalization.

* fix: positional argument.

* handle use_torch_2_0_or_xformers.

* handle post_quant_conv

* handle dtype

* fix: sdxl image processor for tiny ae.

* fix: sdxl image processor for tiny ae.

* unify upcasting logic.

* copied from madness.

* remove trailing whitespace.

* set is_tiny_vae = False

* address PR comments.

* change to AutoencoderTiny

* make act_fn an str throughout

* fix: apply_forward_hook decorator call

* get rid of the special is_tiny_vae flag.

* directly scale the output.

* fix dummies?

* fix: act_fn.

* get rid of the Clamp() layer.

* bring back copied from.

* movement of the blocks to appropriate modules.

* add: docstrings to AutoencoderTiny

* add: documentation.

* changes to the conversion script.

* add doc entry.

* settle tests.

* style

* add one slow test.

* fix

* fix 2

* fix 2

* fix: 4

* fix: 5

* finish integration tests

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* style

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* temporarily disable text encoder loras.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debbuging.

* modify doc.

* rename tests.

* print slices.

* fix: assertions

* 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>

* sdxl lora changes.

* better name replacement.

* better replacement.

* debugging

* debugging

* debugging

* debugging

* debugging

* remove print.

* print state dict keys.

* print

* distingisuih better

* debuggable.

* fxi: tyests

* fix: arg from training script.

* access from class.

* run style

* debug

* save intermediate

* some simplifications for SDXL LoRA

* styling

* unet config is not needed in diffusers format.

* fix: dynamic SGM block mapping for SDXL kohya loras (#4322)

* Use lora compatible layers for linear proj_in/proj_out (#4323)

* improve condition for using the sgm_diffusers mapping

* informative comment.

* load compatible keys and embedding layer maaping.

* Get SDXL 1.0 example lora to load

* simplify

* specif ranks and hidden sizes.

* better handling of k rank and hidden

* debug

* debug

* debug

* debug

* debug

* fix: alpha keys

* add check for handling LoRAAttnAddedKVProcessor

* sanity comment

* modifications for text encoder SDXL

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* denugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* up

* up

* up

* up

* up

* up

* unneeded comments.

* unneeded comments.

* kwargs for the other attention processors.

* kwargs for the other attention processors.

* debugging

* debugging

* debugging

* debugging

* improve

* debugging

* debugging

* more print

* Fix alphas

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* clean up

* clean up.

* debugging

* fix: text

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Batuhan Taskaya <batuhan@python.org>

* [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