GitLab

* 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>

* 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>

* add modelmixin and unets

* remove old model page

* minor fixes

* fix unet2dcondition

* add vqmodel and autoencoderkl

* add rest of models

* fix autoencoderkl path

* fix toctree

* fix toctree again

* apply feedback

* apply feedback

* fix copies

* fix controlnet copy

* fix copies

* 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

⚙️chore(transformer_2d) update function signature for encoder_hidden_states

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

The dimension does not match when `inner_dim` is not equal to `in_channels`.

* added dit model

* import

* initial pipeline

* initial convert script

* initial pipeline

* make style

* raise valueerror

* single function

* rename classes

* use DDIMScheduler

* timesteps embedder

* samples to cpu

* fix var names

* fix numpy type

* use timesteps class for proj

* fix typo

* fix arg name

* flip_sin_to_cos and better var names

* fix C shape cal

* make style

* remove unused imports

* cleanup

* add back patch_size

* initial dit doc

* typo

* Update docs/source/api/pipelines/dit.mdx
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* added copyright license headers

* added example usage and toc

* fix variable names asserts

* remove comment

* added docs

* fix typo

* upstream changes

* set proper device for drop_ids

* added initial dit pipeline test

* update docs

* fix imports

* make fix-copies

* isort

* fix imports

* get rid of more magic numbers

* fix code when guidance is off

* remove block_kwargs

* cleanup script

* removed to_2tuple

* use FeedForward class instead of another MLP

* style

* work on mergint DiTBlock with BasicTransformerBlock

* added missing final_dropout and args to BasicTransformerBlock

* use norm from block

* fix arg

* remove unused arg

* fix call to class_embedder

* use timesteps

* make style

* attn_output gets multiplied

* removed commented code

* use Transformer2D

* use self.is_input_patches

* fix flags

* fixed conversion to use Transformer2DModel

* fixes for pipeline

* remove dit.py

* fix timesteps device

* use randn_tensor and fix fp16 inf.

* timesteps_emb already the right dtype

* fix dit test class

* fix test and style

* fix norm2 usage in vq-diffusion

* added author names to pipeline and lmagenet labels link

* fix tests

* use norm_type as string

* rename dit to transformer

* fix name

* fix test

* set  norm_type = "layer" by default

* fix tests

* do not skip common tests

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

* revert AdaLayerNorm API

* fix norm_type name

* make sure all components are in eval mode

* revert norm2 API

* compact

* finish deprecation

* add slow tests

* remove @

* refactor some stuff

* upload

* Update src/diffusers/pipelines/dit/pipeline_dit.py

* finish more

* finish docs

* improve docs

* finish docs
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: William Berman <WLBberman@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* [Attention] Finish refactor attention file

* correct more

* fix

* more fixes

* correct

* up

* move files a bit

* more refactors

* fix more

* more fixes

* fix more onnx

* make style

* upload

* fix

* up

* fix more

* up again

* up

* small fix

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

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