Skip to content

GitLab

Switch branch/tag
  1. 16 Oct, 2024 1 commit
  3. 14 Oct, 2024 1 commit
    • Yuxuan.Zhang's avatar
      CogView3Plus DiT (#9570) · 8d81564b
      Yuxuan.Zhang authored 
      * merge 9588

* max_shard_size="5GB" for colab running

* conversion script updates; modeling test; refactor transformer

* make fix-copies

* Update convert_cogview3_to_diffusers.py

* initial pipeline draft

* make style

* fight bugs 🐛

🪳

* add example

* add tests; refactor

* make style

* make fix-copies

* add co-author

YiYi Xu <yixu310@gmail.com>

* remove files

* add docs

* add co-author
Co-Authored-By: default avatarYiYi Xu <yixu310@gmail.com>

* fight docs

* address reviews

* make style

* make model work

* remove qkv fusion

* remove qkv fusion tets

* address review comments

* fix make fix-copies error

* remove None and TODO

* for FP16(draft)

* make style

* remove dynamic cfg

* remove pooled_projection_dim as a parameter

* fix tests

---------
Co-authored-by: default avatarAryan <aryan@huggingface.co>
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      8d81564b
  5. 09 Oct, 2024 1 commit
  7. 01 Oct, 2024 1 commit
  9. 17 Sep, 2024 1 commit
  11. 16 Sep, 2024 1 commit
    • Yuxuan.Zhang's avatar
      CogVideoX-5b-I2V support (#9418) · 8336405e
      Yuxuan.Zhang authored 
      

* draft Init

* draft

* vae encode image

* make style

* image latents preparation

* remove image encoder from conversion script

* fix minor bugs

* make pipeline work

* make style

* remove debug prints

* fix imports

* update example

* make fix-copies

* add fast tests

* fix import

* update vae

* update docs

* update image link

* apply suggestions from review

* apply suggestions from review

* add slow test

* make use of learned positional embeddings

* apply suggestions from review

* doc change

* Update convert_cogvideox_to_diffusers.py

* make style

* final changes

* make style

* fix tests

---------
Co-authored-by: default avatarAryan <aryan@huggingface.co>
      8336405e
  13. 09 Sep, 2024 1 commit
    • Igor Filippov's avatar
      [Pipeline] animatediff + vid2vid + controlnet (#9337) · a7361dcc
      Igor Filippov authored 
      * add animatediff + vid2vide + controlnet

* post tests fixes

* PR discussion fixes

* update docs

* change input video to links on HF + update an example

* make quality fix

* fix ip adapter test

* fix ip adapter test input

* update ip adapter test
      a7361dcc
  15. 04 Sep, 2024 1 commit
  17. 02 Sep, 2024 1 commit
    • Aryan's avatar
      [core] Support VideoToVideo with CogVideoX (#9333) · 0e6a8403
      Aryan authored 
      * add vid2vid pipeline for cogvideox

* make fix-copies

* update docs

* fake context parallel cache, vae encode tiling

* add test for cog vid2vid

* use video link from HF docs repo

* add copied from comments; correctly rename test class
      0e6a8403
  19. 27 Aug, 2024 1 commit
  21. 25 Aug, 2024 1 commit
  23. 21 Aug, 2024 1 commit
  25. 14 Aug, 2024 1 commit
  27. 13 Aug, 2024 2 commits
  29. 07 Aug, 2024 2 commits
  31. 06 Aug, 2024 1 commit
  33. 05 Aug, 2024 2 commits
    • YiYi Xu's avatar
      add sentencepiece as a soft dependency (#9065) · bc3c73ad
      YiYi Xu authored 
      

* add sentencepiece as  soft dependency for kolors

* up

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      bc3c73ad
    • Aryan's avatar
      PAG variant for HunyuanDiT, PAG refactor (#8936) · b7058d14
      Aryan authored 
      

* copy hunyuandit pipeline

* pag variant of hunyuan dit

* add tests

* update docs

* make style

* make fix-copies

* Update src/diffusers/pipelines/pag/pag_utils.py

* remove incorrect copied from

* remove pag hunyuan attn procs to resolve conflicts

* add pag attn procs again

* new implementation for pag_utils

* revert pag changes

* add pag refactor back; update pixart sigma

* update pixart pag tests

* apply suggestions from review

Co-Authored-By: yixu310@gmail.com

* make style

* update docs, fix tests

* fix tests

* fix test_components_function since list not accepted as valid __init__ param

* apply patch to fix broken tests
Co-Authored-By: default avatarSayak Paul <spsayakpaul@gmail.com>

* make style

* fix hunyuan tests

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      b7058d14
  35. 02 Aug, 2024 1 commit
    • Sayak Paul's avatar
      [Core] Add PAG support for PixArtSigma (#8921) · 7b98c4cc
      Sayak Paul authored 
      * feat: add pixart sigma pag.

* inits.

* fixes

* fix

* remove print.

* copy paste methods to the pixart pag mixin

* fix-copies

* add documentation.

* add tests.

* remove correction file.

* remove pag_applied_layers

* empty
      7b98c4cc
  37. 01 Aug, 2024 2 commits
  39. 30 Jul, 2024 2 commits
    • Aryan's avatar
      [core] Move community AnimateDiff ControlNet to core (#8972) · e5b94b4c
      Aryan authored 
      

* add animatediff controlnet to core

* make style; remove unused method

* fix copied from comment

* add tests

* changes to make tests work

* add utility function to load videos

* update docs

* update pipeline example

* make style

* update docs with example

* address review comments

* add latest freeinit test from #8969

* LoraLoaderMixin -> StableDiffusionLoraLoaderMixin

* fix docs

* Update src/diffusers/utils/loading_utils.py
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>

* fix: variable out of scope

---------
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      e5b94b4c
    • Yoach Lacombe's avatar
      Stable Audio integration (#8716) · 69e72b1d
      Yoach Lacombe authored 
      

* WIP modeling code and pipeline

* add custom attention processor + custom activation + add to init

* correct ProjectionModel forward

* add stable audio to __initèè

* add autoencoder and update pipeline and modeling code

* add half Rope

* add partial rotary v2

* add temporary modfis to scheduler

* add EDM DPM Solver

* remove TODOs

* clean GLU

* remove att.group_norm to attn processor

* revert back src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

* refactor GLU -> SwiGLU

* remove redundant args

* add channel multiples in autoencoder docstrings

* changes in docsrtings and copyright headers

* clean pipeline

* further cleaning

* remove peft and lora and fromoriginalmodel

* Delete src/diffusers/pipelines/stable_audio/diffusers.code-workspace

* make style

* dummy models

* fix copied from

* add fast oobleck tests

* add brownian tree

* oobleck autoencoder slow tests

* remove TODO

* fast stable audio pipeline tests

* add slow tests

* make style

* add first version of docs

* wrap is_torchsde_available to the scheduler

* fix slow test

* test with input waveform

* add input waveform

* remove some todos

* create stableaudio gaussian projection + make style

* add pipeline to toctree

* fix copied from

* make quality

* refactor timestep_features->time_proj

* refactor joint_attention_kwargs->cross_attention_kwargs

* remove forward_chunk

* move StableAudioDitModel to transformers folder

* correct convert + remove partial rotary embed

* apply suggestions from yiyixuxu -> removing attn.kv_heads

* remove temb

* remove cross_attention_kwargs

* further removal of cross_attention_kwargs

* remove text encoder autocast to fp16

* continue removing autocast

* make style

* refactor how text and audio are embedded

* add paper

* update example code

* make style

* unify projection model forward + fix device placement

* make style

* remove fuse qkv

* apply suggestions from review

* Update src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>

* make style

* smaller models in fast tests

* pass sequential offloading fast tests

* add docs for vae and autoencoder

* make style and update example

* remove useless import

* add cosine scheduler

* dummy classes

* cosine scheduler docs

* better description of scheduler

---------
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      69e72b1d
  41. 26 Jul, 2024 1 commit
    • Aryan's avatar
      [core] AnimateDiff SparseCtrl (#8897) · 5c53ca5e
      Aryan authored 
      * initial sparse control model draft

* remove unnecessary implementation

* copy animatediff pipeline

* remove deprecated callbacks

* update

* update pipeline implementation progress

* make style

* make fix-copies

* update progress

* add partially working pipeline

* remove debug prints

* add model docs

* dummy objects

* improve motion lora conversion script

* fix bugs

* update docstrings

* remove unnecessary model params; docs

* address review comment

* add copied from to zero_module

* copy animatediff test

* add fast tests

* update docs

* update

* update pipeline docs

* fix expected slice values

* fix license

* remove get_down_block usage

* remove temporal_double_self_attention from get_down_block

* update

* update docs with org and documentation images

* make from_unet work in sparsecontrolnetmodel

* add latest freeinit test from #8969

* make fix-copies

* LoraLoaderMixin -> StableDiffsuionLoraLoaderMixin
      5c53ca5e
  43. 12 Jul, 2024 1 commit
  45. 11 Jul, 2024 3 commits
    • Sayak Paul's avatar
      [Core] Add AuraFlow (#8796) · 2261510b
      Sayak Paul authored 
      

* add lavender flow transformer

---------
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      2261510b
    • Álvaro Somoza's avatar
      [Core] Add Kolors (#8812) · 87b9db64
      Álvaro Somoza authored 
      * initial draft
      87b9db64
    • Xin Ma's avatar
      Latte: Latent Diffusion Transformer for Video Generation (#8404) · b8cf84a3
      Xin Ma authored 
      

* add Latte to diffusers

* remove print

* remove print

* remove print

* remove unuse codes

* remove layer_norm_latte and add a flag

* remove layer_norm_latte and add a flag

* update latte_pipeline

* update latte_pipeline

* remove unuse squeeze

* add norm_hidden_states.ndim == 2: # for Latte

* fixed test latte pipeline bugs

* fixed test latte pipeline bugs

* delete sh

* add doc for latte

* add licensing

* Move Transformer3DModelOutput to modeling_outputs

* give a default value to sample_size

* remove the einops dependency

* change norm2 for latte

* modify pipeline of latte

* update test for Latte

* modify some codes for latte

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* video_length -> num_frames; update prepare_latents copied from

* make fix-copies

* make style

* typo: videe -> video

* update

* modify for Latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify for Latte pipeline

* Delete .vscode directory

* make style

* make fix-copies

* add latte transformer 3d to docs _toctree.yml

* update example

* reduce frames for test

* fixed bug of _text_preprocessing

* set num frame to 1 for testing

* remove unuse print

* add text = self._clean_caption(text) again

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
Co-authored-by: default avatarAryan <contact.aryanvs@gmail.com>
Co-authored-by: default avatarAryan <aryan@huggingface.co>
      b8cf84a3
  47. 09 Jul, 2024 1 commit
  49. 08 Jul, 2024 1 commit
  51. 29 Jun, 2024 1 commit
  53. 26 Jun, 2024 1 commit
  55. 25 Jun, 2024 1 commit
  57. 19 Jun, 2024 1 commit
  59. 13 Jun, 2024 1 commit
  61. 12 Jun, 2024 1 commit
  63. 01 Jun, 2024 1 commit
  65. 31 May, 2024 1 commit
    • Sayak Paul's avatar
      [Core] Introduce class variants for `Transformer2DModel` (#7647) · 983dec3b
      Sayak Paul authored 
      * init for patches

* finish patched model.

* continuous transformer

* vectorized transformer2d.

* style.

* inits.

* fix-copies.

* introduce DiTTransformer2DModel.

* fixes

* use REMAPPING as suggested by @DN6

* better logging.

* add pixart transformer model.

* inits.

* caption_channels.

* attention masking.

* fix use_additional_conditions.

* remove print.

* debug

* flatten

* fix: assertion for sigma

* handle remapping for modeling_utils

* add tests for dit transformer2d

* quality

* placeholder for pixart tests

* pixart tests

* add _no_split_modules

* add docs.

* check

* check

* check

* check

* fix tests

* fix tests

* move Transformer output to modeling_output

* move errors better and bring back use_additional_conditions attribute.

* add unnecessary things from DiT.

* clean up pixart

* fix remapping

* fix device_map things in pixart2d.

* replace Transformer2DModel with appropriate classes in dit, pixart tests

* empty

* legacy mixin classes./

* use a remapping dict for fetching class names.

* change to specifc model types in the pipeline implementations.

* move _fetch_remapped_cls_from_config to modeling_loading_utils.py

* fix dependency problems.

* add deprecation note.
      983dec3b