GitLab

* add: a warning message when using xformers in a PT 2.0 env.

* 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>

* clarify safetensor docstring

* fix typo

* apply feedback

* update IF stage I pipelines

add fixed variance schedulers and lora loading

* added kv lora attn processor

* allow loading into alternative lora attn processor

* make vae optional

* throw away predicted variance

* allow loading into added kv lora layer

* allow load T5

* allow pre compute text embeddings

* set new variance type in schedulers

* fix copies

* refactor all prompt embedding code

class prompts are now included in pre-encoding code
max tokenizer length is now configurable
embedding attention mask is now configurable

* fix for when variance type is not defined on scheduler

* do not pre compute validation prompt if not present

* add example test for if lora dreambooth

* add check for train text encoder and pre compute text embeddings

The argument `upsample_size` needs to be added to these modules to allow compatibility with other blocks that require this argument.

* Fix more torch compile breaks

* add tests

* Fix all

* fix controlnet

* fix more

* Add Horace He as co-author.
>
>
Co-authored-by: Horace He <horacehe2007@yahoo.com>

* Add Horace He as co-author.
Co-authored-by: Horace He <horacehe2007@yahoo.com>

---------
Co-authored-by: Horace He <horacehe2007@yahoo.com>

* fix more

* Fix more

* fix more

* Apply suggestions from code review

* fix

* make style

* make fix-copies

* fix

* make sure torch compile

* Clean

* fix test

* Allow disabling torch 2_0 attention

* make style

* Update src/diffusers/models/attention.py

* Add all files

* update

* Make sure vae is memory efficient for PT 1

* make style

* 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>

* Make sure attention works with Torch 2_0

* make style

* Fix more

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

* 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>

⚙️chore(transformer_2d) update function signature for encoder_hidden_states

This mimics the dtype cast for the standard time embeddings

Adding act fn config to the unet timestep class embedding and conv
activation.

The custom activation defaults to silu which is the default
activation function for both the conv act and the timestep class
embeddings so default behavior is not changed.

The only unet which use the custom activation is the stable diffusion
latent upscaler https://huggingface.co/stabilityai/sd-x2-latent-upscaler/blob/main/unet/config.json
(I ran a script against the hub to confirm).
The latent upscaler does not use the conv activation nor the timestep
class embeddings so we don't change its behavior.

* 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>

* add guess mode (WIP)

* fix uncond/cond order

* support guidance_scale=1.0 and batch != 1

* remove magic coeff

* add docstring

* add intergration test

* add document to controlnet.mdx

* made the comments a bit more explanatory

* fix table

* 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 use_memory_efficient params placeholder

* test

* add memory efficient attention jax

* add memory efficient attention jax

* newline

* forgot dot

* Rename use_memory_efficient

* Keep dtype last.

* Actually use key_chunk_size

* Rename symbol

* Apply style

* Rename use_memory_efficient

* Keep dtype last

* Pass `use_memory_efficient_attention` in `from_pretrained`

* Move JAX memory efficient attention to attention_flax.

* Simple test.

* style

---------
Co-authored-by: muhammad_hanif <muhammad_hanif@sofcograha.co.id>
Co-authored-by: MuhHanif <48muhhanif@gmail.com>

add AttnAddedKVProcessor2_0 block

add group norm type to attention processor cross attention norm

This lets the cross attention norm use both a group norm block and a
layer norm block.

The group norm operates along the channels dimension
and requires input shape (batch size, channels, *) where as the layer norm with a single
`normalized_shape` dimension only operates over the least significant
dimension i.e. (*, channels).

The channels we want to normalize are the hidden dimension of the encoder hidden states.

By convention, the encoder hidden states are always passed as (batch size, sequence
length, hidden states).

This means the layer norm can operate on the tensor without modification, but the group
norm requires flipping the last two dimensions to operate on (batch size, hidden states, sequence length).

All existing attention processors will have the same logic and we can
consolidate it in a helper function `prepare_encoder_hidden_states`

prepare_encoder_hidden_states -> norm_encoder_hidden_states re: @patrickvonplaten

move norm_cross defined check to outside norm_encoder_hidden_states

add missing attn.norm_cross check

* unet time embedding activation function

* typo act_fn -> time_embedding_act_fn

* flatten conditional

* ⚙️chore(train_controlnet) fix typo in logger message

* ⚙️chore(models) refactor modules order; make them the same as calling order

When printing the BasicTransformerBlock to stdout, I think it's crucial that the attributes order are shown in proper order. And also previously the "3. Feed Forward" comment was not making sense. It should have been close to self.ff but it's instead next to self.norm3

* correct many tests

* remove bogus file

* make style

* correct more tests

* finish tests

* fix one more

* make style

* make unclip deterministic

* ⚙

️chore(models/attention) reorganize comments in BasicTransformerBlock class

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

* Update documentation

Based on sampling, the width and height must be powers of 2 as the samples halve in size each time

* make style

* `AttentionProcessor.group_norm` num_channels should be `query_dim`

The group_norm on the attention processor should really norm the number
of channels in the query _not_ the inner dim. This wasn't caught before
because the group_norm is only used by the added kv attention processors
and the added kv attention processors are only used by the karlo models
which are configured such that the inner dim is the same as the query
dim.

* add_{k,v}_proj should be projecting to inner_dim

* [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

`encoder_hid_dim` provides an additional projection for the input `encoder_hidden_states` from `encoder_hidden_dim` to `cross_attention_dim`

* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add case for parsing embedding from auto1111 UI format
Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>

* fix style after rebase

* move textual inversion mixin to loaders

* move mixin inheritance to DiffusionPipeline from StableDiffusionPipeline)

* update dummy class name

* addressed allo comments

* fix old dangling import

* fix style

* proposal

* remove bogus

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

* finish

* make style

* up

* fix code quality

* fix code quality - again

* fix code quality - 3

* fix alt diffusion code quality

* fix model editing pipeline

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

* Finish

---------
Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Co-authored-by: njindal <njindal@adobe.com>

Improve init

* Helper function to disable custom attention processors.

* Restore code deleted by mistake.

* Format

* Fix modeling_text_unet copy.

* Apply same ruff settings as in transformers

See https://github.com/huggingface/transformers/blob/main/pyproject.toml

Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* Apply new style rules

* Style
Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* style

* remove list, ruff wouldn't auto fix.

---------
Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* Add AudioLDM

* up

* add vocoder

* start unet

* unconditional unet

* clap, vocoder and vae

* clean-up: conversion scripts

* fix: conversion script token_type_ids

* clean-up: pipeline docstring

* tests: from SD

* clean-up: cpu offload vocoder instead of safety checker

* feat: adapt tests to audioldm

* feat: add docs

* clean-up: amend pipeline docstrings

* clean-up: make style

* clean-up: make fix-copies

* fix: add doc path to toctree

* clean-up: args for conversion script

* clean-up: paths to checkpoints

* fix: use conditional unet

* clean-up: make style

* fix: type hints for UNet

* clean-up: docstring for UNet

* clean-up: make style

* clean-up: remove duplicate in docstring

* clean-up: make style

* clean-up: make fix-copies

* clean-up: move imports to start in code snippet

* fix: pass cross_attention_dim as a list/tuple to unet

* clean-up: make fix-copies

* fix: update checkpoint path

* fix: unet cross_attention_dim in tests

* film embeddings -> class embeddings

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

* fix: unet film embed to use existing args

* fix: unet tests to use existing args

* fix: make style

* fix: transformers import and version in init

* clean-up: make style

* Revert "clean-up: make style"

This reverts commit 5d6d1f8b324f5583e7805dc01e2c86e493660d66.

* clean-up: make style

* clean-up: use pipeline tester mixin tests where poss

* clean-up: skip attn slicing test

* fix: add torch dtype to docs

* fix: remove conversion script out of src

* fix: remove .detach from 1d waveform

* fix: reduce default num inf steps

* fix: swap height/width -> audio_length_in_s

* clean-up: make style

* fix: remove nightly tests

* fix: imports in conversion script

* clean-up: slim-down to two slow tests

* clean-up: slim-down fast tests

* fix: batch consistent tests

* clean-up: make style

* clean-up: remove vae slicing fast test

* clean-up: propagate changes to doc

* fix: increase test tol to 1e-2

* clean-up: finish docs

* clean-up: make style

* feat: vocoder / VAE compatibility check

* feat: possibly expand / cut audio waveform

* fix: pipeline call signature test

* fix: slow tests output len

* clean-up: make style

* make style

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