AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
5,848 Commits 742 Branches 94 Tags
kernelize
Commit Graph

369 Commits

Author SHA1 Message Date
Álvaro Somoza
af92869d9b [SD3 LoRA Training] Fix errors when not training text encoders (#8743) 
* fix

* fix things.

Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>

* remove patch

* apply suggestions

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>
 2024-07-02 06:21:16 +05:30
Linoy Tsaban
c6e08ecd46 [Sd3 Dreambooth LoRA] Add text encoder training for the clip encoders (#8630) 
* add clip text-encoder training

* no dora

* text encoder traing fixes

* text encoder traing fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* add text_encoder layers to save_lora

* style

* fix imports

* style

* fix text encoder

* review changes

* review changes

* review changes

* minor change

* add lora tag

* style

* add readme notes

* add tests for clip encoders

* style

* typo

* fixes

* style

* Update tests/lora/test_lora_layers_sd3.py

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

* Update examples/dreambooth/README_sd3.md

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

* minor readme change

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-25 18:00:19 +05:30
Hammond Liu
1f81fbe274 Fix redundant pipe init in sd3 lora (#8680) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-25 07:31:20 +05:30
Tolga Cangöz
f040c27d4c Errata - Fix typos and improve style (#8571) 
* Fix typos

* Fix typos & up style

* chore: Update numbers

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 10:07:22 -07:00
Tolga Cangöz
468ae09ed8 Errata - Trim trailing white space in the whole repo (#8575) 
* Trim all the trailing white space in the whole repo

* Remove unnecessary empty places

* make style && make quality

* Trim trailing white space

* trim

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 18:39:15 +05:30
Tolga Cangöz
c375903db5 Errata - Fix typos & improve contributing page (#8572) 
* Fix typos & improve contributing page

* `make style && make quality`

* fix typos

* Fix typo

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 14:13:03 +05:30
satani99
963ee05d16 Update train_dreambooth_lora_sd3.py (#8600) 
* 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>
 2024-06-20 17:42:24 +05:30
Sayak Paul
a1d55e14ba Change the default weighting_scheme in the SD3 scripts (#8639) 
* change to logit_normal as the weighting scheme

* sensible default mote
 2024-06-19 13:05:26 +01:00
Sayak Paul
23a2cd3337 [LoRA] training fix the position of param casting when loading them (#8460) 
fix the position of param casting when loading them
 2024-06-18 14:57:34 +01:00
Sayak Paul
4edde134f6 [SD3 training] refactor the density and weighting utilities. (#8591) 
refactor the density and weighting utilities.
 2024-06-18 14:44:38 +01:00
Bagheera
074a7cc3c5 SD3: update default training timestep / loss weighting distribution to logit_normal (#8592) 
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
 2024-06-18 14:15:19 +01:00
Álvaro Somoza
6bfd13f07a [SD3 Training] T5 token limit (#8564) 
* initial commit

* default back to 77

* better text

* text correction

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-17 16:32:56 -04:00
spacepxl
8e1b7a084a Fix the deletion of SD3 text encoders for Dreambooth/LoRA training if the text encoders are not being trained (#8536) 
* Update train_dreambooth_sd3.py to fix TE garbage collection

* Update train_dreambooth_lora_sd3.py to fix TE garbage collection

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-16 20:52:33 +01:00
Rafie Walker
6946facf69 Implement SD3 loss weighting (#8528) 
* Add lognorm and cosmap weighting

* Implement mode sampling

* Update examples/dreambooth/train_dreambooth_lora_sd3.py

* Update examples/dreambooth/train_dreambooth_lora_sd3.py

* Update examples/dreambooth/train_dreambooth_sd3.py

* Update examples/dreambooth/train_dreambooth_sd3.py

* Update examples/dreambooth/train_dreambooth_sd3.py

* Update examples/dreambooth/train_dreambooth_lora_sd3.py

* Update examples/dreambooth/train_dreambooth_sd3.py

* Update examples/dreambooth/train_dreambooth_sd3.py

* Update examples/dreambooth/train_dreambooth_lora_sd3.py

* keep timestamp sampling fully on cpu

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-16 20:15:50 +01:00
Jonathan Rahn
a899e42fc7 add sentencepiece to requirements.txt for SD3 dreambooth (#8538) 
* add `sentencepiece` requirement for SD3

add `sentencepiece` requirement

* Empty-Commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-14 22:48:36 +01:00
Sayak Paul
2e4841ef1e post release 0.29.0 (#8492) 
post release
 2024-06-13 06:14:20 -10:00
Haofan Wang
8bea943714 Update requirements_sd3.txt (#8521) 2024-06-13 17:02:17 +01:00
Ameer Azam
0240d4191a Update README_sd3.md (#8490) 
becasue in  Readme  it was not correct
train_dreambooth_sd3.py to train_dreambooth_lora_sd3
 2024-06-12 21:08:36 +01:00
Dhruv Nair
04717fd861 Add Stable Diffusion 3 (#8483) 
* up

* add sd3

* update

* update

* add tests

* fix copies

* fix docs

* update

* add dreambooth lora

* add LoRA

* update

* update

* update

* update

* import fix

* update

* Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py

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

* import fix 2

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

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

* update

* update

* update

* fix ckpt id

* fix more ids

* update

* missing doc

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py

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

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py

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

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

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

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

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

* update'

* fix

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* note on gated access.

* requirements

* licensing

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-06-12 20:44:00 +01:00
Tolga Cangöz
98730c5dd7 Errata (#8322) 
* Fix typos

* Trim trailing whitespaces

* Remove a trailing whitespace

* chore: Update MarigoldDepthPipeline checkpoint to prs-eth/marigold-lcm-v1-0

* Revert "chore: Update MarigoldDepthPipeline checkpoint to prs-eth/marigold-lcm-v1-0"

This reverts commit fd742b30b4.

* pokemon -> naruto

* `DPMSolverMultistep` -> `DPMSolverMultistepScheduler`

* Improve Markdown stylization

* Improve style

* Improve style

* Refactor pipeline variable names for consistency

* up style
 2024-06-05 13:59:09 -07:00
Sayak Paul
581d8aacf7 post release v0.28.0 (#8286) 
* post release v0.28.0

* style
 2024-05-29 07:13:22 +05:30
Sai-Suraj-27
df2bc5ef28 fix: Fixed few docstrings according to the Google Style Guide (#7717) 
Fixed few docstrings according to the Google Style Guide.
 2024-05-20 10:26:05 -07:00
bssrdf
cdda94f412 fix VAE loading issue in train_dreambooth (#7632) 
* fixed vae loading issue #7619

* rerun make style && make quality

* bring back model_has_vae and add change \ to / in config_file_name on windows os to make match work

* add missing import platform

* bring back import model_info

* make config_file_name OS independent

* switch to using Path.as_posix() to resolve OS dependence

* improve style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: bssrdf <bssrdf@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-05-14 08:19:53 +05:30
Bagheera
8e963d1c2a 7529 do not disable autocast for cuda devices (#7530) 
* 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>
 2024-04-02 20:15:06 +05:30
Bagheera
d78acdedc1 apple mps: training support for SDXL (ControlNet, LoRA, Dreambooth, T2I) (#7447) 
* 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>
 2024-03-28 14:26:18 +05:30
Sayak Paul
288632adf6 [Training utils] add kohya conversion dict. (#7435) 
* add kohya conversion dict.

* update readme

* typo

* add filename
 2024-03-26 17:31:22 +05:30
Sayak Paul
76de6a09fb post-release v0.27.0 (#7329) 
* post-release

* quality
 2024-03-18 10:52:20 +05:30
Sayak Paul
4fbd310fd2 [Chore] switch to logger.warning (#7289) 
switch to logger.warning
 2024-03-13 06:56:43 +05:30
Sayak Paul
9d9744075e [Easy] fix: save_model_card utility of the DreamBooth SDXL LoRA script (#7258) 
* fix: save_model_card utility.

* fix a little more to make it more lenient.

* remove lower()
 2024-03-08 15:22:23 +05:30
Sayak Paul
0d4dfbbd0a [Examples] fix: prior preservation setting in DreamBooth LoRA SDXL script. (#7242) 
fix: prior preservation setting in DreamBooth LoRA SDXL script.

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-03-07 15:19:58 +05:30
Linoy Tsaban
b5814c5555 add DoRA training feature to sdxl dreambooth lora script (#7235) 
* dora in canonical script

* add mention of DoRA to readme
 2024-03-07 11:43:37 +05:30
Linoy Tsaban
8da360aa12 [training scripts] add tags of diffusers-training (#7206) 
* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add dora tags for drambooth lora scripts

* style
 2024-03-04 22:17:25 +05:30
Sayak Paul
ccb93dcad1 Support EDM-style training in DreamBooth LoRA SDXL script (#7126) 
* add: dreambooth lora script for Playground v2.5

* fix: kwarg

* address suraj's comments.

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* apply suraj's suggestion

* incorporate changes in the canonical script./

* tracker naming

* fix: schedule determination

* add: two simple tests

* remove playground script

* note about edm-style training

* address pedro's comments.

* address part of Suraj's comments.

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* remove guidance_scale.

* use mse_loss.

* add comments for preconditioning.

* quality

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* tackle v-pred.

* Empty-Commit

* support edm for sdxl too.

* address suraj's comments.

* Empty-Commit

---------

Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2024-03-03 09:28:57 +05:30
Sayak Paul
5f150c4cef fix: loading problem for sdxl lora dreambooth (#7166) 2024-03-01 19:30:48 +05:30
Sayak Paul
7db935a141 fix kwarg in the SDXL LoRA DreamBooth (#7124) 
* fix kwarg

* Empty-Commit
 2024-02-28 10:21:28 +05:30
Vinh H. Pham
7f16187182 Modularize Dreambooth LoRA SDXL inferencing during and after training (#6655) 
* modularize log validation

* run make style

* revert import wandb

* fix code quality & import wandb

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:53:12 +05:30
Vinh H. Pham
f11b922b4f Modularize Dreambooth LoRA SD inferencing during and after training (#6654) 
* modulize log validation

* run make style and refactor wanddb support

* remove redundant initialization

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:01:39 +05:30
Alex Umnov
e7696e20f9 Updated lora inference instructions (#6913) 
* Updated lora inference instructions

* Update examples/dreambooth/README.md

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

* Update README.md

* Update README.md

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-13 09:35:20 +05:30
Sayak Paul
7c8cab313e post release 0.26.2 (#6885) 
* post release

* style

* Empty-Commit

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-02-09 07:36:38 -10:00
Sayak Paul
159885adc6 correct hub_token exposition behaviour (thanks to @bghira). (#6918) 2024-02-08 18:38:27 -10:00
Sayak Paul
30e5e81d58 change to 2024 in the license (#6902) 
change to 2024
 2024-02-08 08:19:31 -10:00
camaro
4a3d52850b fix: keyword argument mismatch (#6895) 2024-02-08 09:37:56 +05:30
Sayak Paul
76696dca55 [Model Card] standardize dreambooth model card (#6729) 
* feat: standarize model card creation for dreambooth training.

* correct 'inference

* remove comments.

* take component out of kwargs

* style

* add: card template to have a leaner description.

* widget support.

* propagate changes to train_dreambooth_lora

* propagate changes to custom diffusion

* make widget properly type-annotated
 2024-02-07 15:07:11 +05:30
Linoy Tsaban
fbdf26bac5 [dreambooth lora sdxl] add sdxl micro conditioning (#6795) 
* add micro conditioning

* remove redundant lines

* style

* fix missing 's'

* fix missing shape bug due to missing RGB if statement

* remove redundant if, change arg order

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-04 16:00:09 +02:00
Younes Belkada
15ed53d272 Fixes LoRA SDXL training script with DDP + PEFT (#6816) 
Update train_dreambooth_lora_sdxl.py
 2024-02-03 09:46:32 +05:30
Aryan V S
c11de13588 [training] fix training resuming problem for fp16 (SD LoRA DreamBooth) (#6554) 
* fix training resume

* update

* update
 2024-01-16 07:27:06 +05:30
Sayak Paul
a080f0d3a2 [Training Utils] create a utility for casting the lora params during training. (#6553) 
create a utility for casting the lora params during training.
 2024-01-15 13:51:13 +05:30
Sayak Paul
79df50388d [Training] fix training resuming problem when using FP16 (SDXL LoRA DreamBooth) (#6514) 
* fix: training resume from fp16.

* add: comment

* remove residue from another branch.

* remove more residues.

* thanks to Younes; no hacks.

* style.

* clean things a bit and modularize _set_state_dict_into_text_encoder

* add comment about the fix detailed.
 2024-01-12 17:11:06 +05:30
Vinh H. Pham
7d631825b0 Make Dreambooth SD Training Script torch.compile compatible (#6532) 
* support compile

* make style

* move unwrap_model inside function

* change unwrap call

* run make style

* Update examples/dreambooth/train_dreambooth.py

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

* Revert "Update examples/dreambooth/train_dreambooth.py"

This reverts commit 70ab09732e.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-12 12:50:15 +05:30
Vinh H. Pham
60cb44323d Make Dreambooth SD LoRA Training Script torch.compile compatible (#6534) 
support compile
 2024-01-12 09:24:03 +05:30