Skip to content

GitLab

Switch branch/tag
  1. 12 Dec, 2024 3 commits
    • hlky's avatar
      Remove `negative_*` from SDXL callback (#10203) · f2d348d9
      hlky authored 
      * Remove `negative_*` from SDXL callback

* Change example and add XL version
      f2d348d9
    • Sayak Paul's avatar
      [WIP][Training] Flux Control LoRA training script (#10130) · 8170dc36
      Sayak Paul authored 
      

* update

* add

* update

* add control-lora conversion script; make flux loader handle norms; fix rank calculation assumption

* control lora updates

* remove copied-from

* create separate pipelines for flux control

* make fix-copies

* update docs

* add tests

* fix

* Apply suggestions from code review
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* remove control lora changes

* apply suggestions from review

* Revert "remove control lora changes"

This reverts commit 73cfc519c9b99b7dc3251cc6a90a5db3056c4819.

* update

* update

* improve log messages

* updates.

* updates

* support register_config.

* fix

* fix

* fix

* updates

* updates

* updates

* fix-copies

* fix

* apply suggestions from review

* add tests

* remove conversion script; enable on-the-fly conversion

* bias -> lora_bias.

* fix-copies

* peft.py

* fix lora conversion

* changes
Co-authored-by: default avatara-r-r-o-w <contact.aryanvs@gmail.com>

* fix-copies

* updates for tests

* fix

* alpha_pattern.

* add a test for varied lora ranks and alphas.

* revert changes in num_channels_latents = self.transformer.config.in_channels // 8

* revert moe

* add a sanity check on unexpected keys when loading norm layers.

* contro lora.

* fixes

* fixes

* fixes

* tests

* reviewer feedback

* fix

* proper peft version for lora_bias

* fix-copies

* updates

* updates

* updates

* remove debug code

* update docs

* integration tests

* nis

* fuse and unload.

* fix

* add slices.

* more updates.

* button up readme

* train()

* add full fine-tuning version.

* fixes

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

* set_grads_to_none remove.

* readme

---------
Co-authored-by: default avatarAryan <aryan@huggingface.co>
Co-authored-by: default avataryiyixuxu <yixu310@gmail.com>
Co-authored-by: default avatara-r-r-o-w <contact.aryanvs@gmail.com>
      8170dc36
    • Ethan Smith's avatar
      fix min-snr implementation (#8466) · 26e80e01
      Ethan Smith authored 
      * fix min-snr implementation

https://github.com/kohya-ss/sd-scripts/blob/main/library/custom_train_functions.py#L66



* Update train_dreambooth.py

fix variable name mse_loss_weights

* fix divisor

* make style

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      26e80e01
  3. 10 Dec, 2024 3 commits
    • Linoy Tsaban's avatar
      [community pipeline rf-inversion] - fix example in doc (#10179) · 43534a8d
      Linoy Tsaban authored 
      * fix example in doc

* remove redundancies

* change param
      43534a8d
    • hlky's avatar
      Use `torch` in `get_3d_rotary_pos_embed`/`_allegro` (#10161) · 4c4b323c
      hlky authored 
      Use torch in get_3d_rotary_pos_embed/_allegro
      4c4b323c
    • Linoy Tsaban's avatar
      [community pipeline] Add RF-inversion Flux pipeline (#9816) · c9e4fab4
      Linoy Tsaban authored 
      

* initial commit

* update denoising loop

* fix scheduling

* style

* fix import

* fixes

* fixes

* style

* fixes

* change invert

* change denoising & check inputs

* shape & timesteps fixes

* timesteps fixes

* style

* remove redundancies

* small changes

* update documentation a bit

* update documentation a bit

* update documentation a bit

* style

* change strength param, remove redundancies

* style

* forward ode loop change

* add inversion progress bar

* fix image_seq_len

* revert to strength but == 1 by default.

* style

* add "copied from..." comments

* credit authors

* make style

* return inversion outputs without self-assigning

* adjust denoising loop to generate regular images if inverted latents are not provided

* adjust denoising loop to generate regular images if inverted latents are not provided

* fix import

* comment

* remove redundant line

* modify comment on ti

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Update examples/community/pipeline_flux_rf_inversion.py
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* fix syntax error

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarhlky <hlky@hlky.ac>
      c9e4fab4
  5. 06 Dec, 2024 3 commits
  7. 03 Dec, 2024 2 commits
  9. 28 Nov, 2024 3 commits
  11. 27 Nov, 2024 1 commit
  13. 25 Nov, 2024 1 commit
  15. 24 Nov, 2024 1 commit
  17. 19 Nov, 2024 2 commits
  19. 18 Nov, 2024 2 commits
  21. 16 Nov, 2024 1 commit
  23. 13 Nov, 2024 1 commit
  25. 08 Nov, 2024 3 commits
  27. 07 Nov, 2024 1 commit
    • Sayak Paul's avatar
      [Core] introduce `controlnet` module (#8768) · ded3db16
      Sayak Paul authored 
      

* move vae flax module.

* controlnet module.

* prepare for PR.

* revert a commit

* gracefully deprecate controlnet deps.

* fix

* fix doc path

* fix-copies

* fix path

* style

* style

* conflicts

* fix

* fix-copies

* sparsectrl.

* updates

* fix

* updates

* updates

* updates

* fix

---------
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      ded3db16
  29. 06 Nov, 2024 2 commits
  31. 02 Nov, 2024 1 commit
    • Dorsa Rohani's avatar
      Add Diffusion Policy for Reinforcement Learning (#9824) · c10f875f
      Dorsa Rohani authored 
      

* enable cpu ability

* model creation + comprehensive testing

* training + tests

* all tests working

* remove unneeded files + clarify docs

* update train tests

* update readme.md

* remove data from gitignore

* undo cpu enabled option

* Update README.md

* update readme

* code quality fixes

* diffusion policy example

* update readme

* add pretrained model weights + doc

* add comment

* add documentation

* add docstrings

* update comments

* update readme

* fix code quality

* Update examples/reinforcement_learning/README.md
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* Update examples/reinforcement_learning/diffusion_policy.py
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* suggestions + safe globals for weights_only=True

* suggestions + safe weights loading

* fix code quality

* reformat file

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      c10f875f
  33. 01 Nov, 2024 4 commits
  35. 31 Oct, 2024 3 commits
  37. 28 Oct, 2024 3 commits