GitLab

* add lora_alpha and lora_dropout

* Apply style fixes

* add lora_alpha and lora_dropout

* Apply style fixes

* revert lora_alpha until #11324 is merged

* Apply style fixes

* empty commit

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* feat: enable quantization for hidream lora training.

* better handle compute dtype.

* finalize.

* fix dtype.

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* Fix typos in docs and comments

* Apply style fixes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

remove unnecessary pipeline moving to cpu in validation
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* 1. add pre-computation of prompt embeddings when custom prompts are used as well
2. save model card even if model is not pushed to hub
3. remove scheduler initialization from code example - not necessary anymore (it's now if the base model's config)
4. add skip_final_inference - to allow to run with validation, but skip the final loading of the pipeline with the lora weights to reduce memory reqs

* pre encode validation prompt as well

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* pre encode validation prompt as well

* Apply style fixes

* empty commit

* change default trained modules

* empty commit

* address comments + change encoding of validation prompt (before it was only pre-encoded if custom prompts are provided, but should be pre-encoded either way)

* Apply style fixes

* empty commit

* fix validation_embeddings definition

* fix final inference condition

* fix pipeline deletion in last inference

* Apply style fixes

* empty commit

* layers

* remove readme remarks on only pre-computing when instance prompt is provided and change example to 3d icons

* smol fix

* empty commit

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* initial commit

* initial commit

* initial commit

* initial commit

* initial commit

* initial commit

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>

* move prompt embeds, pooled embeds outside

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac>

* fix import

* fix import and tokenizer 4, text encoder 4 loading

* te

* prompt embeds

* fix naming

* shapes

* initial commit to add HiDreamImageLoraLoaderMixin

* fix init

* add tests

* loader

* fix model input

* add code example to readme

* fix default max length of text encoders

* prints

* nullify training cond in unpatchify for temp fix to incompatible shaping of transformer output during training

* smol fix

* unpatchify

* unpatchify

* fix validation

* flip pred and loss

* fix shift!!!

* revert unpatchify changes (for now)

* smol fix

* Apply style fixes

* workaround moe training

* workaround moe training

* remove prints

* to reduce some memory, keep vae in `weight_dtype` same as we have for flux (as it's the same vae)
https://github.com/huggingface/diffusers/blob/bbd0c161b55ba2234304f1e6325832dd69c60565/examples/dreambooth/train_dreambooth_lora_flux.py#L1207



* refactor to align with HiDream refactor

* refactor to align with HiDream refactor

* refactor to align with HiDream refactor

* add support for cpu offloading of text encoders

* Apply style fixes

* adjust lr and rank for train example

* fix copies

* Apply style fixes

* update README

* update README

* update README

* fix license

* keep prompt2,3,4 as None in validation

* remove reverse ode comment

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* vae offload change

* fix text encoder offloading

* Apply style fixes

* cleaner to_kwargs

* fix module name in copied from

* add requirements

* fix offloading

* fix offloading

* fix offloading

* update transformers version in reqs

* try AutoTokenizer

* try AutoTokenizer

* Apply style fixes

* empty commit

* Delete tests/lora/test_lora_layers_hidream.py

* change tokenizer_4 to load with AutoTokenizer as well

* make text_encoder_four and tokenizer_four configurable

* save model card

* save model card

* revert T5

* fix test

* remove non diffusers lumina2 conversion

---------
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* post release

* update

* fix deprecations

* remaining

* update

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

* update

* update

* update

* update

* Fix seed initialization to handle args.seed = 0 correctly

* Apply style fixes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* feat: lora support for Lumina2.

* fix-copies.

* updates

* updates

* docs.

* fix

* add: training script.

* tests

* updates

* updates

* major updates.

* updates

* fixes

* docs.

* updates

* updates

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* [bugfix]NPU Adaption for Sanna

---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* NPU Adaption for Sanna


---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

change licensing to 2025 from 2024.

Co-authored-by: J石页 <jiangshuo9@h-partners.com>

* post release 0.32.0

* stylew

* sana lora training tests and misc.

* remove push to hub

* Update examples/dreambooth/train_dreambooth_lora_sana.py
Co-authored-by: Aryan <aryan@huggingface.co>

---------
Co-authored-by: Aryan <aryan@huggingface.co>

* feat: lora support for SANA.

* make fix-copies

* rename test class.

* attention_kwargs -> cross_attention_kwargs.

* Revert "attention_kwargs -> cross_attention_kwargs."

This reverts commit 23433bf9bccc12e0f2f55df26bae58a894e8b43b.

* exhaust 119 max line limit

* sana lora fine-tuning script.

* readme

* add a note about the supported models.

* Apply suggestions from code review
Co-authored-by: Aryan <aryan@huggingface.co>

* style

* docs for attention_kwargs.

* remove lora_scale from pag pipeline.

* copy fix

---------
Co-authored-by: Aryan <aryan@huggingface.co>

* memory improvement as done here: https://github.com/huggingface/diffusers/pull/9829



* fix bug

* fix bug

* style

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

* Improve NPU performance

* Improve NPU performance

* Improve NPU performance

* Improve NPU performance

* [bugfix] bugfix for npu free memory

* [bugfix] bugfix for npu free memory

* [bugfix] bugfix for npu free memory

* Reduce memory cost for flux training process

---------
Co-authored-by: 蒋硕 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

Handling mixed precision and add unwarp
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* use the lr when using 8bit adam.

* remove lr as we pack it in params_to_optimize.

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* make lora target modules configurable and change the default

* style

* make lora target modules configurable and change the default

* fix bug when using prodigy and training te

* fix mixed precision training as  proposed in https://github.com/huggingface/diffusers/pull/9565

 for full dreambooth as well

* add test and notes

* style

* address sayaks comments

* style

* fix test

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

[Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script (#9473)

* fix: removed setting of text encoder lr for T5 as it's not being tuned

* fix: removed setting of text encoder lr for T5 as it's not being tuned

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* flux pipline: readability enhancement.

* post-release

* style

* fixed issue #9350, Tensor is deprecated

* ran make style

* fix: retain memory utility.

* fix

* quality

* free_memory.

* add ostris trainer to README & add cache latents of vae

* add ostris trainer to README & add cache latents of vae

* style

* readme

* add test for latent caching

* add ostris noise scheduler
https://github.com/ostris/ai-toolkit/blob/9ee1ef2a0a2a9a02b92d114a95f21312e5906e54/toolkit/samplers/custom_flowmatch_sampler.py#L95



* style

* fix import

* style

* fix tests

* style

* --change upcasting of transformer?

* update readme according to main

* keep only latent caching

* add configurable param for final saving of trained layers- --upcast_before_saving

* style

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

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

* use clear_objs_and_retain_memory from utilities

* style

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

* Fix dtype error

* [bugfix] Fixed the issue on sd3 dreambooth training

* [bugfix] Fixed the issue on sd3 dreambooth training

---------
Co-authored-by: 蒋硕 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

fix some fast gpu tests.

* post release

* fix quality

* add requirements + fix link to bghira's guide

* text ecnoder training fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* style

* add tests

* fix encode_prompt call

* style

* unpack_latents test

* fix lora saving

* remove default val for max_sequenece_length in encode_prompt

* remove default val for max_sequenece_length in encode_prompt

* style

* testing

* style

* testing

* testing

* style

* fix sizing issue

* style

* revert scaling

* style

* style

* scaling test

* style

* scaling test

* remove model pred operation left from pre-conditioning

* remove model pred operation left from pre-conditioning

* fix trainable params

* remove te2 from casting

* transformer to accelerator

* remove prints

* empty commit

* initial commit - dreambooth for flux

* update transformer to be FluxTransformer2DModel

* update training loop and validation inference

* fix sd3->flux docs

* add guidance handling, not sure if it makes sense(?)

* inital dreambooth lora commit

* fix text_ids in compute_text_embeddings

* fix imports of static methods

* fix pipeline loading in readme, remove auto1111 docs for now

* fix pipeline loading in readme, remove auto1111 docs for now, remove some irrelevant text_encoder_3 refs

* Update examples/dreambooth/train_dreambooth_flux.py
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>

* fix te2 loading and remove te2 refs from text encoder training

* fix tokenizer_2 initialization

* remove text_encoder training refs from lora script (for now)

* try with vae in bfloat16, fix model hook save

* fix tokenization

* fix static imports

* fix CLIP import

* remove text_encoder training refs (for now) from lora script

* fix minor bug in encode_prompt, add guidance def in lora script, ...

* fix unpack_latents args

* fix license in readme

* add "none" to weighting_scheme options for uniform sampling

* style

* adapt model saving - remove text encoder refs

* adapt model loading - remove text encoder refs

* initial commit for readme

* Update examples/dreambooth/train_dreambooth_lora_flux.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_flux.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* fix vae casting

* remove precondition_outputs

* readme

* readme

* style

* readme

* readme

* update weighting scheme default & docs

* style

* add text_encoder training to lora script, change vae_scale_factor value in both

* style

* text encoder training fixes

* style

* update readme

* minor fixes

* fix te params

* fix te params

---------
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* SD3 training fixes
Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>

* rewrite noise addition part to respect the eqn.

* styler

* Update examples/dreambooth/README_sd3.md
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>

---------
Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>

* Improve trainer model cards

* Update train_dreambooth_sd3.py

* Update train_dreambooth_lora_sd3.py

* add link to adapters loading doc

* Update train_dreambooth_lora_sd3.py

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* Fix typos & improve contributing page

* `make style && make quality`

* fix typos

* Fix typo

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

* Update train_dreambooth_lora_sd3.py

* Update train_dreambooth_lora_sd3.py

* Update train_dreambooth_sd3.py

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

* change to logit_normal as the weighting scheme

* sensible default mote

refactor the density and weighting utilities.

Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>