d6a70d8ba8
Bump jinja2 from 3.1.2 to 3.1.3 in /examples/research_projects/realfill ( #6539 )
...
Bumps [jinja2](https://github.com/pallets/jinja ) from 3.1.2 to 3.1.3.
- [Release notes](https://github.com/pallets/jinja/releases )
- [Changelog](https://github.com/pallets/jinja/blob/main/CHANGES.rst )
- [Commits](https://github.com/pallets/jinja/compare/3.1.2...3.1.3 )
---
updated-dependencies:
- dependency-name: jinja2
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-01-15 16:10:10 +02:00
e3103e171f
Make InstructPix2Pix SDXL Training Script torch.compile compatible ( #6576 )
...
* changes for pix2pix_sdxl
* style fix
2024-01-15 17:54:03 +05:30
b053053ac9
Make InstructPix2Pix Training Script torch.compile compatible ( #6558 )
...
* added torch.compile for pix2pix
* required changes
2024-01-15 17:03:22 +05:30
08702fc1cb
Make text-to-image SDXL LoRA Training Script torch.compile compatible ( #6556 )
...
make compile compatible
2024-01-15 16:58:16 +05:30
7ce89e979c
Make text-to-image SD LoRA Training Script torch.compile compatible ( #6555 )
...
make compile compatible
2024-01-15 16:55:08 +05:30
05faf3263b
SDXL text-to-image torch compatible ( #6550 )
...
* torch compatible
* code quality fix
* ruff style
* ruff format
2024-01-15 16:49:11 +05:30
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
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
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 70ab09732espsayakpaul@gmail.com >
2024-01-12 12:50:15 +05:30
33d2b5b087
SD text-to-image torch compile compatible ( #6519 )
...
* added unwrapper
* fiz typo
2024-01-12 09:28:35 +05:30
f486d34b04
Make ControlNet SD Training Script torch.compile compatible ( #6525 )
...
* update: make controlnet script torch compile compatible
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com >
* update: correct earlier mistakes for compilation
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com >
* update: fix code style issues
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com >
---------
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com >
2024-01-12 09:27:26 +05:30
e44b205e0b
Make ControlNet SDXL Training Script torch.compile compatible ( #6526 )
...
* make torch.compile compatible
* fix quality
2024-01-12 09:25:09 +05:30
60cb44323d
Make Dreambooth SD LoRA Training Script torch.compile compatible ( #6534 )
...
support compile
2024-01-12 09:24:03 +05:30
1dd0ac9401
[DPO Training] pass tracker name as argument ( #6542 )
...
pass tracker name as argumentw
2024-01-12 09:15:39 +05:30
9df566e6da
[Community] StyleAligned Pipeline ( #6489 )
...
* add stylealigned sdxl pipeline
* bugfix
* update docs
* remove einops dependency
* update README
* update example docstring
2024-01-11 14:35:55 +01:00
be0b425762
[Training] make checkpointing compatible when using torch.compile (part II) ( #6511 )
...
make checkpointing compatible when using torch.compile.
2024-01-11 18:37:30 +05:30
17cece072a
Fix bug in LCM Distillation Scripts when args.unet_time_cond_proj_dim is used ( #6523 )
...
* Fix bug where unet's time_cond_proj_dim is not set correctly if using args.unet_time_cond_proj_dim.
* make style
2024-01-11 08:21:07 +05:30
2d1f2182cc
example: Train Instruct pix2 pix with lora implementation ( #6469 )
...
* base template file - train_instruct_pix2pix.py
* additional import and parser argument requried for lora
* finetune only instructpix2pix model -- no need to include these layers
* inject lora layers
* freeze unet model -- only lora layers are trained
* training modifications to train only lora parameters
* store only lora parameters
* move train script to research project
* run quality and style code checks
* move train script to a new folder
* add README
* update README
* update references in README
---------
Co-authored-by: Rahul Raman <rahulraman@gmail.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-10 06:38:19 +05:30
4497b3ec98
[Training] make DreamBooth SDXL LoRA training script compatible with torch.compile ( #6483 )
...
* make it torch.compile comaptible
* make the text encoder compatible too.
* style
2024-01-09 20:11:26 +05:30
fc63ebdd3a
[Community Pipeline] Rerender-A-Video: Zero-Shot Video-to-Video Translation ( #6332 )
...
* upload codes and doc
* lint
* lint
* lint
* update code
* remove blank lines
* Fix load url
2024-01-09 14:55:34 +01:00
aa1797e109
enable stable-xl textual inversion ( #6421 )
...
* enable stable-xl textual inversion
* check if optimizer_2 exists
* check text_encoder_2 before using
* add textual inversion for sdxl in a single file
* fix style
* fix example style
* reset for error changes
* add readme for sdxl
* fix style
* disable autocast as it will cause cast error when weight_dtype=bf16
* fix spelling error
* fix style and readme and 8bit optimizer
* add README_sdxl.md link
* add tracker key on log_validation
* run style
* rm the second center crop
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-09 15:12:33 +05:30
a483a8eddf
Rename REAMDE.md to README.md
2024-01-05 20:49:44 +05:30
3848606c7e
[Community Pipeline] Add gluegen ( #6433 )
...
* init works
* add gluegen pipeline
* add gluegen code
* add another way to load language adapter
* make style
* Update README.md
* change doc
2024-01-05 13:05:40 +01:00
2a97067b84
[Experimental] Diffusion LoRA DPO training ( #6422 )
...
* add: experimental script for diffusion dpo training.
* random_crop cli.
* fix: caption tokenization.
* fix: pixel_values index.
* fix: grad?
* debug
* fix: reduction.
* fixes in the loss calculation.
* style
* fix: unwrap call.
* fix: validation inference.
* add: initial sdxl script
* debug
* make sure images in the tuple are of same res
* fix model_max_length
* report print
* boom
* fix: numerical issues.
* fix: resolution
* comment about resize.
* change the order of the training transformation.
* save call.
* debug
* remove print
* manually detaching necessary?
* use the same vae for validation.
* add: readme.
2024-01-05 16:40:06 +05:30
9d945b2b90
0.25.0 post release ( #6358 )
...
* post release
* style
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2024-01-05 16:13:27 +05:30
d184291c7d
null-text-inversion-pipeline-implementation ( #6329 )
...
* null-text-inversion-implementation
* edited
* edited
* edited
* edited
* edited
* edit
* makestyle
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-05 11:35:21 +01:00
2fada8dc1b
[bug fix] fixes #6444 - checkpointing save issue in advanced dreambooth lora sdxl script ( #6464 )
...
* unwrap text encoder when saving hook only for full text encoder tuning
* unwrap text encoder when saving hook only for full text encoder tuning
* save embeddings in each checkpoint as well
* save embeddings in each checkpoint as well
* save embeddings in each checkpoint as well
* Update examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-05 15:35:24 +05:30
f2d51a28f7
Intel Gen 4 Xeon and later support bf16 ( #6367 )
...
* Intel Gen 4 Xeon and later support bf16
* fix bf16 notes
2024-01-05 11:47:28 +05:30
f3d1333e02
Improve LCM(-LoRA) Distillation Scripts ( #6420 )
...
* Make WDS pipeline interpolation type configurable.
* Make the VAE encoding batch size configurable.
* Make lora_alpha and lora_dropout configurable for LCM LoRA scripts.
* Generalize scalings_for_boundary_conditions function and make the timestep scaling configurable.
* Make LoRA target modules configurable for LCM-LoRA scripts.
* Move resolve_interpolation_mode to src/diffusers/training_utils.py and make interpolation type configurable in non-WDS script.
* apply suggestions from review
2024-01-05 06:55:13 +05:30
aad18faa3e
Update README_sdxl.md to update the LR ( #6432 )
...
Update README_sdxl.md
2024-01-03 20:55:51 +05:30
d700140076
[LoRA deprecation] handle rest of the stuff related to deprecated lora stuff. ( #6426 )
...
* handle rest of the stuff related to deprecated lora stuff.
* fix: copies
* don't modify the uNet in-place.
* fix: temporal autoencoder.
* manually remove lora layers.
* don't copy unet.
* alright
* remove lora attn processors from unet3d
* fix: unet3d.
* styl
* Empty-Commit
2024-01-03 20:54:09 +05:30
e30b661437
Update lpw_xl pipeline to latest diffusers ( #6411 )
...
* add clip_skip, freeu, qkv
* fix
* add ip-adapter support
* callback on step end
* update
* fix NoneType bug
* fix
* add guidance scale embedding
* add textual inversion
2024-01-02 16:28:45 +01:00
b4077af212
[bug fix] using snr gamma and prior preservation loss in the dreambooth lora sdxl training scripts ( #6356 )
...
* change timesteps used to calculate snr when --with_prior_preservation is enabled
* change timesteps used to calculate snr when --with_prior_preservation is enabled (canonical script)
* style
* revert canonical script to before snr gamma change
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-02 09:21:39 -06:00
8a366b835c
Fix gradient-checkpointing option is ignored in SDXL+LoRA training. ( #6388 ) ( #6402 )
...
* Fix gradient-checkpointing option is ignored in SDXL+LoRA training. (#6388 )
* Fix gradient-checkpointing option is ignored in SD+LoRA training.
* Fix gradient checkpoint is not applied to text encoders. (SDXL+LoRA)
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-01-01 08:51:04 +05:30
1622265e13
Add WebUI format support to Advanced Training Script ( #6403 )
...
* Add WebUI format support to Advanced Training Script
* style
---------
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com >
2023-12-30 08:45:49 -06:00
9f283b01d2
changed w&b report link ( #6387 )
2023-12-29 19:49:11 +05:30
e7044a4221
multi-subject-dreambooth-inpainting with 🤗 datasets ( #6378 )
...
* files added
* fixing code quality
* fixing code quality
* fixing code quality
* fixing code quality
* sorted import block
* seperated import wandb
* ruff on script
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-29 09:33:49 +05:30
1ac07d8a8d
[Training examples] Follow up of #6306 ( #6346 )
...
* add to dreambooth lora.
* add: t2i lora.
* add: sdxl t2i lora.
* style
* lcm lora sdxl.
* unwrap
* fix: enable_adapters().
2023-12-28 07:37:50 +05:30
1fff527702
Fix keys for lora format on advanced training scripts ( #6361 )
...
fix keys for lora format on advanced training scripts
2023-12-27 11:38:03 -06:00
645a62bf3b
Add PEFT to advanced training script ( #6294 )
...
* Fix ProdigyOPT in SDXL Dreambooth script
* style
* style
* Add PEFT to Advanced Training Script
* style
* style
* ✨ style ✨
* change order for logic operation
* add lora alpha
* style
* Align PEFT to new format
* Update train_dreambooth_lora_sdxl_advanced.py
Apply #6355 fix
---------
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com >
2023-12-27 10:00:32 -03:00
43672b4a22
Fix "push_to_hub only create repo in consistency model lora SDXL training script" ( #6102 )
...
* fix
* style fix
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-27 15:25:19 +05:30
9df3d84382
Fix LCM distillation bug when creating the guidance scale embeddings using multiple GPUs. ( #6279 )
...
Fix bug when creating the guidance embeddings using multiple GPUs.
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-27 14:25:21 +05:30
c751449011
fix: use retrieve_latents ( #6337 )
2023-12-27 10:44:26 +05:30
c1e8bdf1d4
Move ControlNetXS into Community Folder ( #6316 )
...
* update
* update
* update
* update
* update
* make style
* remove docs
* update
* move to research folder.
* fix-copies
* remove _toctree entry.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-27 08:15:23 +05:30
78b87dc25a
[LoRA] make LoRAs trained with peft loadable when peft isn't installed ( #6306 )
...
* spit diffusers-native format from the get go.
* rejig the peft_to_diffusers mapping.
2023-12-27 08:01:10 +05:30
0af12f1f8a
amused update links to new repo ( #6344 )
...
* amused update links to new repo
* lint
2023-12-26 22:46:28 +01:00
fa31704420
[SDXL-IP2P] Update README_sdxl, Replace the link for wandb log with the correct run ( #6270 )
...
Replace the link for wandb log with the correct run
2023-12-26 21:13:11 +01:00
6683f97959
[Training] Add datasets version of LCM LoRA SDXL ( #5778 )
...
* add: script to train lcm lora for sdxl with 🤗 datasets
* suit up the args.
* remove comments.
* fix num_update_steps
* fix batch unmarshalling
* fix num_update_steps_per_epoch
* fix; dataloading.
* fix microconditions.
* unconditional predictions debug
* fix batch size.
* no need to use use_auth_token
* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com >
* make vae encoding batch size an arg
* final serialization in kohya
* style
* state dict rejigging
* feat: no separate teacher unet.
* debug
* fix state dict serialization
* debug
* debug
* debug
* remove prints.
* remove kohya utility and make style
* fix serialization
* fix
* add test
* add peft dependency.
* add: peft
* remove peft
* autocast device determination from accelerator
* autocast
* reduce lora rank.
* remove unneeded space
* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com >
* style
* remove prompt dropout.
* also save in native diffusers ckpt format.
* debug
* debug
* debug
* better formation of the null embeddings.
* remove space.
* autocast fixes.
* autocast fix.
* hacky
* remove lora_sayak
* Apply suggestions from code review
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com >
* style
* make log validation leaner.
* move back enabled in.
* fix: log_validation call.
* add: checkpointing tests
* taking my chances to see if disabling autocasting has any effect?
* start debugging
* name
* name
* name
* more debug
* more debug
* index
* remove index.
* print length
* print length
* print length
* move unet.train() after add_adapter()
* disable some prints.
* enable_adapters() manually.
* remove prints.
* some changes.
* fix params_to_optimize
* more fixes
* debug
* debug
* remove print
* disable grad for certain contexts.
* Add support for IPAdapterFull (#5911 )
* Add support for IPAdapterFull
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Fix a bug in `add_noise` function (#6085 )
* fix
* copies
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
* [Advanced Diffusion Script] Add Widget default text (#6100 )
add widget
* [Advanced Training Script] Fix pipe example (#6106 )
* IP-Adapter for StableDiffusionControlNetImg2ImgPipeline (#5901 )
* adapter for StableDiffusionControlNetImg2ImgPipeline
* fix-copies
* fix-copies
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* IP adapter support for most pipelines (#5900 )
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py
* update tests
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_panorama.py
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
* support ip-adapter in src/diffusers/pipelines/stable_diffusion_safe/pipeline_stable_diffusion_safe.py
* support ip-adapter in src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py
* support ip-adapter in src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py
* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_ldm3d.py
* revert changes to sd_attend_and_excite and sd_upscale
* make style
* fix broken tests
* update ip-adapter implementation to latest
* apply suggestions from review
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* fix: lora_alpha
* make vae casting conditional/
* param upcasting
* propagate comments from https://github.com/huggingface/diffusers/pull/6145
Co-authored-by: dg845 <dgu8957@gmail.com >
* [Peft] fix saving / loading when unet is not "unet" (#6046 )
* [Peft] fix saving / loading when unet is not "unet"
* Update src/diffusers/loaders/lora.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* undo stablediffusion-xl changes
* use unet_name to get unet for lora helpers
* use unet_name
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* [Wuerstchen] fix fp16 training and correct lora args (#6245 )
fix fp16 training
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* [docs] fix: animatediff docs (#6339 )
fix: animatediff docs
* add: note about the new script in readme_sdxl.
* Revert "[Peft] fix saving / loading when unet is not "unet" (#6046 )"
This reverts commit 4c7e983bb5#6245 )"
This reverts commit 0bb9cf0216#6339 )"
This reverts commit 11659a6f74surajp815@gmail.com >
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com >
Co-authored-by: Fabio Rigano <57982783+fabiorigano@users.noreply.github.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: apolinário <joaopaulo.passos@gmail.com >
Co-authored-by: Charchit Sharma <charchitsharma11@gmail.com >
Co-authored-by: Aryan V S <contact.aryanvs@gmail.com >
Co-authored-by: dg845 <dgu8957@gmail.com >
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com >
2023-12-26 21:22:05 +05:30
35b81fffae
[Wuerstchen] fix fp16 training and correct lora args ( #6245 )
...
fix fp16 training
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-26 11:40:04 +01:00
a3d31e3a3e
Change LCM-LoRA README Script Example Learning Rates to 1e-4 ( #6304 )
...
Change README LCM-LoRA example learning rates to 1e-4.
2023-12-25 21:29:20 +05:30
dependabot[bot]