GitLab

* find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor

* Remove dead code

* PylancereportGeneralTypeIssues: Strings nested within an f-string cannot use the same quote character as the f-string prior to Python 3.12.

* Remove dead code

* edited_pag_implementation

* update

---------
Co-authored-by: yiyixuxu <yixu310@gmail.com>

* 7879 - adjust documentation to use naruto dataset, since pokemon is now gated

* replace references to pokemon in docs

* more references to pokemon replaced

* Japanese translation update

---------
Co-authored-by: bghira <bghira@users.github.com>

Add Ascend NPU support for SDXL fine-tuning and fix the model saving bug when using DeepSpeed. (#7816)

* Add Ascend NPU support for SDXL fine-tuning and fix the model saving bug when using DeepSpeed.

* fix check code quality

* Decouple the NPU flash attention and make it an independent module.

* add doc and unit tests for npu flash attention.

---------
Co-authored-by: mhh001 <mahonghao1@huawei.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* up

* add comment to the tests + fix dit

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

* add blora

* add blora

* add blora

* add blora

* little changes

* little changes

* remove redundancies

* fixes

* add B LoRA to readme

* style

* inference

* defaults + path to loras+ generation

* minor changes

* style

* minor changes

* minor changes

* blora arg

* added --lora_unet_blocks

* style

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

* add commit hash to B-LoRA repo cloneing

* change inference, remove cloning

* change inference, remove cloning
add section about configureable unet blocks

* change inference, remove cloning
add section about configureable unet blocks

* Apply suggestions from code review

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

* Check for latents, before calling prepare_latents - sdxlImg2Img

* Added latents check for all the img2img pipeline

* Fixed silly mistake while checking latents as None

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>

* toctree

* optim

* feedback

* improve overview

* fixed encode_image function signature in controlnet animatediff

* copied encode_image from stable diffusion pipeline

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Fixed type annotations for compatability with python 3.8

* Add required imports.

update

* Switch to peft and multi proj layers

* Move Face ID loading and inference to core

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

* 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>

* 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 https://github.com/kohya-ss/sd-scripts/pull/1228/commits/c6495def1fbbaf2a0233110d50f976ed61620e83

* [DB Lora] add option for smooth l1 (huber / delta)

Pairing of https://github.com/kohya-ss/sd-scripts/pull/1228/commits/dd22958caa56e4db885324f76188c13bdf504569

* [DB Lora] unify huber scheduling

Pairing of https://github.com/kohya-ss/sd-scripts/pull/1228/commits/19a834c3ab448614e8887b07f2bb4e0aaabf0805

* [DB Lora] add snr huber scheduler

Pairing of https://github.com/kohya-ss/sd-scripts/pull/1228/commits/47fb1a68547e76f33cd54a3da8d2c35b9489c56e



* 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>

* 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>

* Modularize instruct_pix2pix code

* quality check

* quality check

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

* Restore unet params back to normal from EMA when validation call is finished

* empty commit

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

* 7529 do not disable autocast for cuda devices

* Remove typecasting error check for non-mps platforms, as a correct autocast implementation makes it a non-issue

* add autocast fix to other training examples

* disable native_amp for dreambooth (sdxl)

* disable native_amp for pix2pix (sdxl)

* remove tests from remaining files

* disable native_amp on huggingface accelerator for every training example that uses it

* convert more usages of autocast to nullcontext, make style fixes

* make style fixes

* style.

* Empty-Commit

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

* initial-commit pipeline created

* updated README.md

* add from_pipe



---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* add HD-Painter pipeline

* style fixing

* refactor, change doc, fix ruff

* fix docs

* used correct ruff version

---------
Co-authored-by: Hayk Manukyan <youremail@yourdomain.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* add resample option; check denoise_step; update ckpt path

* Add seeding in pipeline to increase reproducibility

* fix typo

* fix typo

* pag_initial

* pag_docs

* edit_docs

* custom

* typo

* delete_docs

* whitespace

* make style

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

* initial commit - instantid img2img

* adapting to img2img

* change add_time_ids

* change add_time_ids

* WIP changes

* add strength to timesteps

* check insightface import

* style

* check insightface import changed to warning

* check insightface import changed to warning

* style

---------
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>

* apple mps: training support for SDXL LoRA

* sdxl: support training lora, dreambooth, t2i, pix2pix, and controlnet on apple mps

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

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

* add kohya conversion dict.

* update readme

* typo

* add filename

you cannot specify `type="bool"` and `action="store_true"` at the same time.
remove excessive and buggy `type=bool`.
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

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

* fixed typo

* updated doc to be consistent in naming

* make style/quality

* preprocessing for 4 channels and not 6

* make style

* test for 4c

* make style/quality

* fixed test on cpu

* fixed doc typo

* changed default ckpt to 4c

* Update pipeline_stable_diffusion_ldm3d.py

* fix bug

---------
Co-authored-by: Aflalo <estellea@isl-iam1.rr.intel.com>
Co-authored-by: Aflalo <estellea@isl-gpu33.rr.intel.com>
Co-authored-by: Aflalo <estellea@isl-gpu38.rr.intel.com>

* Fix typos

* Fix typos

* Fix typos

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

* barebones orpo

* remove reference model.

* full implementation

* change default of beta_orpo

* add a training command.

* fix: dataloading issues.

* interpreting the formulation.

* revert styling

* add: wds full blown version

* fix: per_gpu_batch_siz

* start debuggin

* debugging

* remove print

* fix

* remove filter keys.

* turn on non-blocking calls.

* device_placement

* let's see.

* add bigger training run command

* reinitialize generator for fair repro

* add: detailed readme and requirements

---------
Co-authored-by: Sayak Paul <sayakpaul@Sayaks-MacBook-Pro-2.local>

* add

* add tiling

* fix

* fix

* fix

* give community script its own readme

* Update examples/community/README_community_scripts.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update examples/community/README_community_scripts.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update examples/community/README_community_scripts.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update examples/community/README_community_scripts.md

---------
Co-authored-by: Alexis Rolland <alexis.rolland@ubisoft.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Fix typos

* Fix typo in SVD.md

* cleanse and refactor lora testing suite.

* more cleanup.

* make check_if_lora_correctly_set a utility function

* fix: typo

* retrigger ci

* style

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

* Fix PyTorch's convention for inplace functions

* Fix import structure in __init__.py and update config loading logic in test_config.py

* Update configuration access

* Fix typos

* Trim trailing white spaces

* Fix typo in logger name

* Revert "Fix PyTorch's convention for inplace functions"

This reverts commit f65dc4afcb57ceb43d5d06389229d47bafb10d2d.

* Fix typo in step_index property description

* Revert "Update configuration access"

This reverts commit 8d44e870b8c1ad08802e3e904c34baeca1b598f8.

* Revert "Fix import structure in __init__.py and update config loading logic in test_config.py"

This reverts commit 2ad5e8bca25aede3b912da22bd57285b598fe171.

* Fix typos

* Fix typos

* Fix typos

* Fix a typo: tranform -> transform