Jenyuan-Huang
5fcb90f180
Update InstantStyle usage in IP-Adapter documentation ( #7806 )
...
* enable control ip-adapter per-transformer block on-the-fly
---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com >
Co-authored-by: ResearcherXman <xhs.research@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-23 13:02:11 +05:30
Sayak Paul
0211759f5c
[Scheduler] introduce sigma schedule. ( #7649 )
...
* introduce sigma schedule.
Co-authored-by: Suraj Patil <surajp815@gmail.com >
* address yiyi
* update docstrings.
* implement the schedule for EDMDPMSolverMultistepScheduler
---------
Co-authored-by: Suraj Patil <surajp815@gmail.com >
2024-12-23 13:02:11 +05:30
39th president of the United States, probably
d5f2a8c88c
Add DREAM training ( #6381 )
...
A new function compute_dream_and_update_latents has been added to the
training utilities that allows you to do DREAM rectified training in line
with the paper https://arxiv.org/abs/2312.00210 . The method can be used
with an extra argument in the train_text_to_image.py script.
Co-authored-by: Jimmy <39@🇺🇸 .com>
2024-12-23 13:02:11 +05:30
Fabio Rigano
ec8ce0c2a0
[Docs] Update image masking and face id example ( #7780 )
...
* [Docs] Update image masking and face id example
* Update docs
* Fix docs
2024-12-23 13:02:11 +05:30
Beinsezii
b43b87d507
Add PixArtSigmaPipeline to AutoPipeline mapping ( #7783 )
2024-12-23 13:02:11 +05:30
Steven Liu
bf1957f6d4
[docs] Fix AutoPipeline docstring ( #7779 )
...
fix
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:11 +05:30
btlorch
4188f306c4
Convert RGB to BGR for the SDXL watermark encoder ( #7013 )
...
* Convert channel order to BGR for the watermark encoder. Convert the watermarked BGR images back to RGB. Fixes #6292
* Revert channel order before stacking images to overcome limitations that negative strides are currently not supported
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:11 +05:30
Steven Liu
de414618ba
[docs] Refactor image quality docs ( #7758 )
...
* refactor
* code snippets
* fix path
* fix path in guide
* code outputs
* align toctree title
* title
* fix title
2024-12-23 13:02:11 +05:30
Steven Liu
bebfb61c5c
[docs] Reproducible pipelines ( #7769 )
...
* reproducibility
* feedback
* feedback
* fix path
* github link
2024-12-23 13:02:11 +05:30
Sayak Paul
513fea53eb
Fix lora device test ( #7738 )
...
* fix lora device test
* fix more.
* fix more/
* quality
* empty
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-12-23 13:02:11 +05:30
Sayak Paul
8373a61a95
[Tests] mark UNetControlNetXSModelTests::test_forward_no_control to be flaky ( #7771 )
...
decorate UNetControlNetXSModelTests::test_forward_no_control with is_flaky
2024-12-23 13:02:11 +05:30
Sayak Paul
b4d6d464d0
[PixArt] fix small nits in pixart sigma ( #7767 )
...
fix small nits in pixart sigma
2024-12-23 13:02:11 +05:30
Junsong Chen
55d7ad64ea
PixArt-Sigma Implementation ( #7654 )
...
* support PixArt-DMD
---------
Co-authored-by: jschen <chenjunsong4@h-partners.com >
Co-authored-by: badayvedat <badayvedat@gmail.com >
Co-authored-by: Vedat Baday <54285744+badayvedat@users.noreply.github.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-12-23 13:02:11 +05:30
Dhruv Nair
9de95b0b96
Fix test for consistency decoder. ( #7746 )
...
update
2024-12-23 13:02:11 +05:30
Dhruv Nair
77d3449200
Fix failing VAE tiling test ( #7747 )
...
update
2024-12-23 13:02:11 +05:30
Steven Liu
ed20a5ac49
[docs] Clean up toctree ( #7715 )
...
* toctree
* optim
* feedback
* improve overview
2024-12-23 13:02:11 +05:30
Sayak Paul
9bef15a567
[Metadat utils] fix: json lines ordering. ( #7744 )
...
fix: json lines ordering.
2024-12-23 13:02:11 +05:30
Sai-Suraj-27
5e66907fda
fix: Fixed a wrong decorator by modifying it to @classmethod ( #7653 )
...
* Fixed wrong decorator by modifying it to @classmethod.
* Updated the method and it's argument.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Fabio Rigano
030b9de0df
Restore AttnProcessor2_0 in unload_ip_adapter ( #7727 )
...
* Restore AttnProcessor2_0 in unload_ip_adapter
* Fix style
* Update test
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-23 13:02:10 +05:30
Jenyuan-Huang
4ec19bc3d5
Support InstantStyle ( #7668 )
...
* enable control ip-adapter per-transformer block on-the-fly
---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com >
Co-authored-by: ResearcherXman <xhs.research@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-23 13:02:10 +05:30
Phil Butler
26f6b4c596
Remove redundant lines ( #7396 )
...
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-23 13:02:10 +05:30
Steven Liu
1cce2c1c25
[docs] AutoPipeline ( #7714 )
...
* autopipeline
* edits
* feedback
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Dhruv Nair
4b518b4a6e
Fix Kandinksy V22 tests ( #7699 )
...
update
2024-12-23 13:02:10 +05:30
Dhruv Nair
6e888b0a69
Update Wuerschten Test ( #7700 )
...
update
2024-12-23 13:02:10 +05:30
Abhinav Gopal
024fb640e0
Animatediff Controlnet Community Pipeline IP Adapter Fix ( #7413 )
...
* fixed encode_image function signature in controlnet animatediff
* copied encode_image from stable diffusion pipeline
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-23 13:02:10 +05:30
Guillaume LEGENDRE
3cf49fd38f
fix/add tailscale key in case of failure ( #7719 )
...
add tailscale key in case of failure
2024-12-23 13:02:10 +05:30
Sai-Suraj-27
20b5919ab2
fix: Fixed type annotations for compatability with python 3.8 ( #7648 )
...
* Fixed type annotations for compatability with python 3.8
* Add required imports.
2024-12-23 13:02:10 +05:30
Dhruv Nair
eb75ed9110
Cleanup ControlnetXS ( #7701 )
...
* update
* update
2024-12-23 13:02:10 +05:30
Dhruv Nair
5f5c806d9c
Cast height, width to int inside prepare latents ( #7691 )
...
update
2024-12-23 13:02:10 +05:30
YiYi Xu
cd4743d978
adding back test_conversion_when_using_device_map ( #7704 )
...
* style
* Fix device map nits (#7705 )
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Fabio Rigano
c5a2b97bff
Move IP Adapter Face ID to core ( #7186 )
...
* Switch to peft and multi proj layers
* Move Face ID loading and inference to core
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Guillaume LEGENDRE
bb07c28442
Add tailscale action to push_test ( #7709 )
2024-12-23 13:02:10 +05:30
Steven Liu
2bed2f4c45
[docs] Pipeline loading ( #7684 )
...
* pipelines
* schedulers and models
* community pipelines
* feedback
2024-12-23 13:02:10 +05:30
Wentian
ff3e9587d9
[Docs] Update TGATE in section optimization. ( #7698 )
...
Update tgate.md
2024-12-23 13:02:10 +05:30
Sayak Paul
d01453e437
[Workflows] remove installation of redundant modules from flax PR tests ( #7662 )
...
remove installation of redundant modules from flax PR tests
2024-12-23 13:02:10 +05:30
Dhruv Nair
d166f496b6
Don't install PEFT with UV in slow tests ( #7697 )
...
* update
* update
2024-12-23 13:02:10 +05:30
Sai-Suraj-27
2b16db59f1
fix: Updated ruff configuration to avoid deprecated configuration warning ( #7637 )
...
Updated ruff configuration to avoid depreceated config.
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Wentian
92125c6887
[Docs] Add TGATE in section optimization ( #7639 )
...
* Create tgate.md
* Update _toctree.yml
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/optimization/tgate.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update tgate.md
* Update tgate.md
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2024-12-23 13:02:10 +05:30
Sayak Paul
4e28bea1bc
[Core] is_cosxl_edit arg in SDXL ip2p. ( #7650 )
...
* is_cosxl_edit arg in SDXL ip2p.
* Empty-Commit
Co-authored-by: Yiyi Xu <yixu310@gmail.com >
* doc
* remove redundant logic.
* reflect drhuv's comments.
---------
Co-authored-by: Yiyi Xu <yixu310@gmail.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-12-23 13:02:10 +05:30
UmerHA
d7895dfa9d
Fixing implementation of ControlNet-XS ( #6772 )
...
* CheckIn - created DownSubBlocks
* Added extra channels, implemented subblock fwd
* Fixed connection sizes
* checkin
* Removed iter, next in forward
* Models for SD21 & SDXL run through
* Added back pipelines, cleared up connections
* Cleaned up connection creation
* added debug logs
* updated logs
* logs: added input loading
* Update umer_debug_logger.py
* log: Loading hint
* Update umer_debug_logger.py
* added logs
* Changed debug logging
* debug: added more logs
* Fixed num_norm_groups
* Debug: Logging all of SDXL input
* Update umer_debug_logger.py
* debug: updated logs
* checkim
* Readded tests
* Removed debug logs
* Fixed Slow Tests
* Added value ckecks | Updated model_cpu_offload_seq
* accelerate-offloading works ; fast tests work
* Made unet & addon explicit in controlnet
* Updated slow tests
* Added dtype/device to ControlNetXS
* Filled in test model paths
* Added image_encoder/feature_extractor to XL pipe
* Fixed fast tests
* Added comments and docstrings
* Fixed copies
* Added docs ; Updates slow tests
* Moved changes to UNetMidBlock2DCrossAttn
* tiny cleanups
* Removed stray prints
* Removed ip adapters + freeU
- Removed ip adapters + freeU as they don't make sense for ControlNet-XS
- Fixed imports of UNet components
* Fixed test_save_load_float16
* Make style, quality, fix-copies
* Changed loading/saving API for ControlNetXS
- Changed loading/saving API for ControlNetXS
- other small fixes
* Removed ControlNet-XS from research examples
* Make style, quality, fix-copies
* Small fixes
- deleted ControlNetXSModel.init_original
- added time_embedding_mix to StableDiffusionControlNetXSPipeline .from_pretrained / StableDiffusionXLControlNetXSPipeline.from_pretrained
- fixed copy hints
* checkin May 11 '23
* CheckIn Mar 12 '24
* Fixed tests for SD
* Added tests for UNetControlNetXSModel
* Fixed SDXL tests
* cleanup
* Delete Pipfile
* CheckIn Mar 20
Started replacing sub blocks by `ControlNetXSCrossAttnDownBlock2D` and `ControlNetXSCrossAttnUplock2D`
* check-in Mar 23
* checkin 24 Mar
* Created init for UNetCnxs and CnxsAddon
* CheckIn
* Made from_modules, from_unet and no_control work
* make style,quality,fix-copies & small changes
* Fixed freezing
* Added gradient ckpt'ing; fixed tests
* Fix slow tests(+compile) ; clear naming confusion
* Don't create UNet in init ; removed class_emb
* Incorporated review feedback
- Deleted get_base_pipeline / get_controlnet_addon for pipes
- Pipes inherit from StableDiffusionXLPipeline
- Made module dicts for cnxs-addon's down/mid/up classes
- Added support for qkv fusion and freeU
* Make style, quality, fix-copies
* Implemented review feedback
* Removed compatibility check for vae/ctrl embedding
* make style, quality, fix-copies
* Delete Pipfile
* Integrated review feedback
- Importing ControlNetConditioningEmbedding now
- get_down/mid/up_block_addon now outside class
- renamed `do_control` to `apply_control`
* Reduced size of test tensors
For this, added `norm_num_groups` as parameter everywhere
* Renamed cnxs-`Addon` to cnxs-`Adapter`
- `ControlNetXSAddon` -> `ControlNetXSAdapter`
- `ControlNetXSAddonDownBlockComponents` -> `DownBlockControlNetXSAdapter`, and similarly for mid/up
- `get_mid_block_addon` -> `get_mid_block_adapter`, and similarly for mid/up
* Fixed save_pretrained/from_pretrained bug
* Removed redundant code
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-12-23 13:02:10 +05:30
Sayak Paul
5301343fc9
don't install peft from the source with uv for now. ( #7679 )
2024-12-23 13:02:10 +05:30
Sayak Paul
a761390f12
fix: metadata token ( #7631 )
2024-12-23 13:02:10 +05:30
Sayak Paul
ab34f394df
make docker-buildx mandatory. ( #7652 )
2024-12-23 13:02:10 +05:30
kabachuha
679d7231e7
Add (Scheduled) Pseudo-Huber Loss training scripts to research projects ( #7527 )
...
* add scheduled pseudo-huber loss training scripts
See #7488
* add reduction modes to huber loss
* [DB Lora] *2 multiplier to huber loss cause of 1/2 a^2 conv.
pairing of c6495def1f
* [DB Lora] add option for smooth l1 (huber / delta)
Pairing of dd22958caa
* [DB Lora] unify huber scheduling
Pairing of 19a834c3ab
* [DB Lora] add snr huber scheduler
Pairing of 47fb1a6854
* fixup examples link
* use snr schedule by default in DB
* update all huber scripts with snr
* code quality
* huber: make style && make quality
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Benjamin Bossan
a0662fdb27
FIX Setting device for DoRA parameters ( #7655 )
...
Fix a bug that causes the the call to set_lora_device to ignore the DoRA
parameters.
2024-12-23 13:02:10 +05:30
Sai-Suraj-27
499d96bfd1
fix: Replaced deprecated logger.warn with logger.warning ( #7643 )
...
Fixed deprecated logger.warn with logger.warning.
2024-12-23 13:02:10 +05:30
Yiqin Zhao
d47de39a46
Fixed YAML loading. ( #7579 )
2024-12-23 13:02:10 +05:30
dg845
6edad9389c
LCM Distill Scripts Fix Bug when Initializing Target U-Net ( #6848 )
...
* Initialize target_unet from unet rather than teacher_unet so that we correctly add time_embedding.cond_proj if necessary.
* Use UNet2DConditionModel.from_config to initialize target_unet from unet's config.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-23 13:02:10 +05:30
Steven Munn
9fffbee44f
Skip PEFT LoRA Scaling if the scale is 1.0 ( #7576 )
...
* Skip scaling if scale is identity
* move check for weight one to scale and unscale lora
* fix code style/quality
* Empty-Commit
---------
Co-authored-by: Steven Munn <stevenjmunn@gmail.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: Steven Munn <5297082+stevenjlm@users.noreply.github.com >
2024-12-23 13:02:10 +05:30
Sayak Paul
42dab12780
[Core] fix img2img pipeline for Playground ( #7627 )
...
* playground vae encoding should use std and mean of the vae.
* style.
* fix-copies.
2024-12-23 13:02:10 +05:30