obscura/diffusers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3,750 Commits 711 Branches 93 Tags
862caee47ac0b9efe2c2b03f9b8c4ff0145802f2
Commit Graph

828 Commits

Author SHA1 Message Date
jiqing-feng 862caee47a Resize image before crop (#7095) 
resize first

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:08 +05:30
Aryan be2e28383a [Community] Bug fix + Latest IP-Adapter impl. for AnimateDiff img2vid/controlnet (#7086) 
* fix img2vid; update to latest ip-adapter impl

* update README

* update animatediff controlnet to latest impl
 2024-12-23 13:02:08 +05:30
Vinh H. Pham 1e6a865d37 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>
 2024-12-23 13:02:08 +05:30
Vinh H. Pham 4ff83c7f4f 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>
 2024-12-23 13:02:08 +05:30
Aryan 23e6b32139 Fix truthy-ness condition in pipelines that use denoising_start (#6912) 
* fix denoising start

* fix tests

* remove debug
 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz 302b3c6b79 [Refactor] StableDiffusionReferencePipeline inheriting from DiffusionPipeline (#7071) 
Refactor StableDiffusionReferencePipeline to inherit from DiffusionPipeline rather than StableDiffusionPipeline
 2024-12-23 13:02:08 +05:30
caiyueliang bc9b342fa4 fix: TensorRTStableDiffusionPipeline cannot set guidance_scale (#7065) 2024-12-23 13:02:08 +05:30
Chong-U Lim eba9562560 Fix docstring of community pipeline imagic (#7062) 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz d38521afa2 Fix typos (#7068) 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz 1f3ff03c01 [Refactor] save_model_card function in text_to_image examples (#7051) 
* Refactor save_model_card function to handle images and repo_folder parameters

* Discard changes to examples/text_to_image/train_text_to_image.py

* Discard changes to examples/text_to_image/train_text_to_image_lora_sdxl.py

* Update train_text_to_image_lora.py

* Update train_text_to_image_sdxl.py
 2024-12-23 13:02:08 +05:30
Lincoln Stein 2f7c83fefb Update checkpoint_merger pipeline to pass the "variant" argument (#6670) 
* make checkpoint_merger pipeline pass the "variant" argument to from_pretrained()

* make style

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz 38c8227fde Fix typos in text_to_image examples (#7050) 
Update copyright information and fix typos in text_to_image examples
 2024-12-23 13:02:08 +05:30
pravdomil 7342038b31 update header (#6596) 
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:08 +05:30
ustcuna 7df14bf40f [Community Pipelines]Accelerate inference of stable diffusion xl (SDXL) by IPEX on CPU (#6683) 
* add stable_diffusion_xl_ipex community pipeline

* make style for code quality check

* update docs as suggested

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-12-23 13:02:08 +05:30
Bhavay Malhotra 2f3c3fd6e7 Update textual_inversion.py (#6952) 
* Update textual_inversion.py

* Apply suggestions from code review

* Update textual_inversion.py

* Update textual_inversion.py

* Update textual_inversion.py

* Update textual_inversion.py

* Update examples/textual_inversion/textual_inversion.py

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

* Update textual_inversion.py

* styling

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:07 +05:30
Stephen 56637cb949 Standardize model card for textual inversion sdxl (#6963) 
* standardize model card

* fix tags

* correct import styling and update tags

* run make style and make quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:07 +05:30
co63oc c8a06e0c20 Fix procecss process (#6591) 
* Fix words

* Fix

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:07 +05:30
Paakhhi 2e90dae0ef Fix diffusers import prompt2prompt (#6927) 
* Bugfix: correct import for diffusers

* Fix: Prompt2Prompt example

* Format style

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:07 +05:30
Linoy Tsaban 8183a770e7 [advanced sdxl lora script] - fix #6967 bug when using prior preservation loss (#6968) 
* fix bug in micro-conditioning of class images

* fix bug in micro-conditioning of class images

* style
 2024-12-23 13:02:07 +05:30
Alex Umnov 9477fa618b 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>
 2024-12-23 13:02:07 +05:30
Piyush Thakur 1b885c2d9a [Type annotations] fixed in save_model_card (#6948) 
fixed type annotations

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:07 +05:30
Piyush Thakur 1974ec76a9 [Model Card] standardize T2I Adapter Sdxl model card (#6947) 
standardize model card template t21-adapter-sdxl
 2024-12-23 13:02:07 +05:30
Piyush Thakur 60a8bf7639 [Model Card] standardize T2I Sdxl Lora model card (#6944) 
* standardize model card template t2i-lora-sdxl

* type annotations
 2024-12-23 13:02:07 +05:30
Piyush Thakur 3cc84918d5 [Model Card] standardize T2I Sdxl model card (#6942) 
standardize model card template t2i-sdxl
 2024-12-23 13:02:07 +05:30
Piyush Thakur 6edce9ad71 [Model Card] standardize T2I Lora model card (#6940) 
standardize model card t2i-lora
 2024-12-23 13:02:07 +05:30
Piyush Thakur 40ca5be078 [Model Card] standardize T2I model card (#6939) 
* standardize model card

* fix base_model
 2024-12-23 13:02:07 +05:30
Sayak Paul 166641aefa post release 0.26.2 (#6885) 
* post release

* style

* Empty-Commit

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-12-23 13:02:07 +05:30
Bingxin Ke fa4a64ca8d [Community Pipeline][Bug Fix] marigold_depth_estimation: input image value range (#6787) 
[FIX] IMPORTANT: rgb normalization
 2024-12-23 13:02:07 +05:30
camaro 181230a64d Standardize model card for Controlnet (#6910) 
* controlnet

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:07 +05:30
Sayak Paul 72d23f5309 correct hub_token exposition behaviour (thanks to @bghira). (#6918) 2024-12-23 13:02:07 +05:30
camaro ecfe845374 Standardize model card for Controlnet SDXL (#6908) 
controlnet-sdxl
 2024-12-23 13:02:07 +05:30
camaro d65f583758 Standardize model card for Controlnet flax (#6909) 
* controlnet-flax

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:07 +05:30
C Q 6d7c1c8530 Fix Compatibility Issues in stable_diffusion_xl_reference.py (#6251) 
* Fix Compatibility Issues in stable_diffusion_xl_reference.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:07 +05:30
shaoxiaowang 8f4e6538e4 fix examples/community/pipeline_stable_diffusion_xl_instantid.py (#6759) 
Co-authored-by: wangshaoxiao <wangshaoxiao@xiaomi.com>
 2024-12-23 13:02:07 +05:30
Michael 075b63882e Remove <cat-toy> validation prompt from examples/textual_inversion/textual_inversion_sdxl.py (#6877) 
Remove <cat-toy> validation prompt from textual_inversion_sdxl.py

The `<cat-toy>` validation prompt is a default choice for the example task in the README. But no other part of `textual_inversion_sdxl.py` references the cat toy and `textual_inversion.py` has a default validation prompt of `None` as well.

So bring `textual_inversion_sdxl.py` in line with `textual_inversion.py` and change default validation prompt to `None`
 2024-12-23 13:02:07 +05:30
Sayak Paul 86e62ae4c5 change to 2024 in the license (#6902) 
change to 2024
 2024-12-23 13:02:07 +05:30
Srimanth Agastyaraju e37350a03a Fix: training resume from fp16 for SDXL Consistency Distillation (#6840) 
* Fix: training resume from fp16 for lcm distill lora sdxl

* Fix coding quality - run linter

* Fix 1 - shift mixed precision cast before optimizer

* Fix 2 - State dict errors by removing load_lora_into_unet

* Update train_lcm_distill_lora_sdxl.py - Revert default cache dir to None

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:06 +05:30
camaro 14aaf03f7d fix: keyword argument mismatch (#6895) 2024-12-23 13:02:06 +05:30
Sayak Paul 3a06d3a15e [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
 2024-12-23 13:02:06 +05:30
YiYi Xu 03aa6bb279 add self.use_ada_layer_norm_* params back to BasicTransformerBlock (#6841) 
fix sd reference community ppeline

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-12-23 13:02:06 +05:30
Linoy Tsaban 7f5335214a [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>
 2024-12-23 13:02:06 +05:30
Fabio Rigano 0e39ac0f41 Bugfix in IPAdapterFaceID (#6835) 2024-12-23 13:02:06 +05:30
Linoy Tsaban 75c5710669 [advanced dreambooth lora sdxl script] new features + bug fixes (#6691) 
* add noise_offset param

* micro conditioning - wip

* image processing adjusted and moved to support micro conditioning

* change time ids to be computed inside train loop

* change time ids to be computed inside train loop

* change time ids to be computed inside train loop

* time ids shape fix

* move token replacement of validation prompt to the same section of instance prompt and class prompt

* add offset noise to sd15 advanced script

* fix token loading during validation

* fix token loading during validation in sdxl script

* a little clean

* style

* a little clean

* style

* sdxl script - a little clean + minor path fix

sd 1.5 script - change default resolution value

* ad 1.5 script - minor path fix

* fix missing comma in code example in model card

* clean up commented lines

* style

* remove time ids computed outside training loop - no longer used now that we utilize micro-conditioning, as all time ids are now computed inside the training loop

* style

* [WIP] - added draft readme, building off of examples/dreambooth/README.md

* readme

* readme

* readme

* readme

* readme

* readme

* readme

* readme

* removed --crops_coords_top_left from CLI args

* style

* fix missing shape bug due to missing RGB if statement

* add blog mention at the start of the reamde as well

* Update examples/advanced_diffusion_training/README.md

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

* change note to render nicely as well

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:06 +05:30
Younes Belkada af99e2ec1b Fixes LoRA SDXL training script with DDP + PEFT (#6816) 
Update train_dreambooth_lora_sdxl.py
 2024-12-23 13:02:06 +05:30
Kashif Rasul 6a7cfa2a20 add ipo, hinge and cpo loss to dpo trainer (#6788) 
add ipo and hinge loss to dpo trainer
 2024-12-23 13:02:06 +05:30
Viet Nguyen 7d2cbd8576 Update train_diffusion_dpo.py (#6754) 
* Update train_diffusion_dpo.py

Address #6702

* Update train_diffusion_dpo_sdxl.py

* Empty-Commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:06 +05:30
Sajad Norouzi c9180c5ef8 Fix mixed precision fine-tuning for text-to-image-lora-sdxl example. (#6751) 
* Fix mixed precision fine-tuning for text-to-image-lora-sdxl example.

* fix text_encoder_two bug.

---------

Co-authored-by: Sajad Norouzi <sajadn@dev-dsk-sajadn-2a-87239470.us-west-2.amazon.com>
 2024-12-23 13:02:06 +05:30
Sayak Paul 85e2b87341 correct hflip arg (#6743) 2024-12-23 13:02:06 +05:30
Yingtian Liu 3daae1cf73 Correct SNR weighted loss in v-prediction case by only adding 1 to SNR on the denominator (#6307) 
* fix minsnr implementation for v-prediction case

* format code

* always compute snr when snr_gamma is specified

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:06 +05:30
dg845 99e4287dee Add UFOGenScheduler to Community Examples (#6650) 
* Add UFOGenScheduler with diffusers imports changed from relative to absolute.

* make style

* Add community README entry for UFOGenScheduler.
 2024-12-23 13:02:06 +05:30