Sayak Paul
6269045c5b
[Refactor] move diffedit out of stable_diffusion ( #6260 )
...
* move diffedit out of stable_diffuson
* fix: import
* style
* fix: import
2023-12-21 12:26:36 +05:30
lvzi
6ca9c4af05
fix: unscale fp16 gradient problem & potential error ( #6086 ) ( #6231 )
...
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-21 09:09:26 +05:30
dependabot[bot]
0532cece97
Bump transformers from 4.34.0 to 4.36.0 in /examples/research_projects/realfill ( #6255 )
...
Bump transformers in /examples/research_projects/realfill
Bumps [transformers](https://github.com/huggingface/transformers ) from 4.34.0 to 4.36.0.
- [Release notes](https://github.com/huggingface/transformers/releases )
- [Commits](https://github.com/huggingface/transformers/compare/v4.34.0...v4.36.0 )
---
updated-dependencies:
- dependency-name: transformers
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-12-21 09:03:17 +05:30
Sayak Paul
22b45304bf
[Refactor upsamplers and downsamplers] separate out upsamplers and downsamplers. ( #6128 )
...
* separate out upsamplers and downsamplers.
* import all the necessary blocks in resnet for backward comp.
* move upsample2d and downsample2d to utils.
* move downsample_2d to downsamplers.py
* apply feedback
* fix import
* samplers -> sampling
2023-12-20 21:01:33 +05:30
Beinsezii
457abdf2cf
EulerAncestral add rescale_betas_zero_snr ( #6187 )
...
* EulerAncestral add `rescale_betas_zero_snr`
Uses same infinite sigma fix from EulerDiscrete. Interestingly the
ancestral version had the opposite problem: too much contrast instead of
too little.
* UT for EulerAncestral `rescale_betas_zero_snr`
* EulerAncestral upcast samples during step()
It helps this scheduler too, particularly when the model is using bf16.
While the noise dtype is still the model's it's automatically upcasted
for the add so all it affects is determinism.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-20 13:09:25 +05:30
hako-mikan
ff43dba7ea
[Fix] Fix Regional Prompting Pipeline ( #6188 )
...
* Update regional_prompting_stable_diffusion.py
* reformat
* reformat
* reformat
* reformat
* reformat
* reformat
* reformat
* regormat
* reformat
* reformat
* reformat
* reformat
* Update regional_prompting_stable_diffusion.py
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-20 10:37:19 +05:30
Steven Liu
5433962992
[docs] Batched seeds ( #6237 )
...
batched seed
2023-12-19 16:50:18 -08:00
raven
df476d9f63
[Docs] Fix a code example in the ControlNet Inpainting documentation ( #6236 )
...
fix document on masked image in inpainting controlnet
2023-12-19 13:14:37 -08:00
YiYi Xu
3e71a20650
[refactor embeddings]pixart-alpha ( #6212 )
...
pixart-alpha
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-12-19 07:07:24 -10:00
Sayak Paul
bf40d7d82a
add peft dependency to fast push tests ( #6229 )
...
* add peft dependency
* add peft dependency at the correct place.
2023-12-19 13:26:25 +05:30
Dhruv Nair
32ff4773d4
ControlNetXS fixes. ( #6228 )
...
update
2023-12-19 11:58:34 +05:30
Sayak Paul
288ceebea5
[T2I LoRA training] fix: unscale fp16 gradient problem ( #6119 )
...
* fix: unscale fp16 gradient problem
* fix for dreambooth lora sdxl
* make the type-casting conditional.
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-12-19 09:54:17 +05:30
Sayak Paul
9221da4063
fix: init for vae during pixart tests ( #6215 )
...
* fix: init for vae during pixart tests
* print the values
* add flatten
* correct assertion value for test_inference
* correct assertion values for test_inference_non_square_images
* run styling
* debug test_inference_with_multiple_images_per_prompt
* fix assertion values for test_inference_with_multiple_images_per_prompt
2023-12-18 18:16:57 -10:00
YiYi Xu
57fde871e1
offload the optional module image_encoder ( #6151 )
...
* offload image_encoder
* add test
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-18 15:10:01 -10:00
Fabio Rigano
68e962395c
Add converter method for ip adapters ( #6150 )
...
* Add converter method for ip adapters
* Move converter method
* Update to image proj converter
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-18 13:46:43 -10:00
Dhruv Nair
781775ea56
Slow Test for Pipelines minor fixes ( #6221 )
...
update
2023-12-19 00:45:51 +05:30
Patrick von Platen
fa3c86beaf
[SVD] Fix guidance scale ( #6002 )
...
* [SVD] Fix guidance scale
* make style
2023-12-18 19:33:24 +01:00
Haofan Wang
7d0a47f387
Update train_text_to_image_lora.py ( #6144 )
...
* Update train_text_to_image_lora.py
* Fix typo?
---------
Co-authored-by: M. Tolga Cangöz <46008593+standardAI@users.noreply.github.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-18 19:33:05 +01:00
Aryan V S
67b3d3267e
Support img2img and inpaint in lpw-xl ( #6114 )
...
* add img2img and inpaint support to lpw-xl
* update community README
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-18 19:19:11 +01:00
TilmannR
4e77056885
Update README.md ( #6191 )
...
Typo: The script for LoRA training is `train_text_to_image_lora_prior.py` not `train_text_to_image_prior_lora.py`.
Alternatively you could rename the file and keep the README.md unchanged.
2023-12-18 19:08:29 +01:00
Dhruv Nair
a0c54828a1
Deprecate Pipelines ( #6169 )
...
* deprecate pipe
* make style
* update
* add deprecation message
* format
* remove tests for deprecated pipelines
* remove deprecation message
* make style
* fix copies
* clean up
* clean
* clean
* clean
* clean up
* clean up
* clean up toctree
* clean up
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-12-18 23:08:29 +05:30
Patrick von Platen
8d891e6e1b
[Torch Compile] Fix torch compile for svd vae ( #6217 )
2023-12-18 18:21:17 +01:00
Patrick von Platen
cce1fe2d41
[Text-to-Video] Clean up pipeline ( #6213 )
...
* make style
* make style
* make style
* make style
2023-12-18 18:21:09 +01:00
Abin Thomas
d816bcb5e8
Fix t2i. blog url ( #6205 )
2023-12-18 09:12:28 -08:00
d8ahazard
6976cab7ca
Fix possible re-conversion issues after extracting from safetensors ( #6097 )
...
* Fix possible re-conversion issues after extracting from diffusers
Properly rename specific vae keys.
* Whoops
2023-12-18 11:51:20 +01:00
Dhruv Nair
fcbed3fa79
Fix SDXL Inpainting from single file with Refiner Model ( #6147 )
...
* update
* update
* update
2023-12-18 11:45:37 +01:00
Sayak Paul
b98b314b7a
[Training] remove depcreated method from lora scripts. ( #6207 )
...
remove depcreated method from lora scripts.
2023-12-18 15:52:43 +05:30
Omar Sanseviero
74558ff65b
Nit fix to training params ( #6200 )
2023-12-18 11:06:16 +01:00
Yudong Jin
49644babd3
Fix the test script in examples/text_to_image/README.md ( #6209 )
...
* Update examples/text_to_image/README.md
* Update examples/text_to_image/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-18 15:36:00 +05:30
Sayak Paul
56b3b21693
[Refactor autoencoders] feat: introduce autoencoders module ( #6129 )
...
* feat: introduce autoencoders module
* more changes for styling and copy fixing
* path changes in the docs.
* fix: import structure in init.
* fix controlnetxs import
2023-12-18 12:42:15 +05:30
Sayak Paul
9cef07da5a
[Benchmarks] fix: lcm benchmarking reporting ( #6198 )
...
* fix: lcm benchmarking reporting
* fix generate_csv_dict call.
2023-12-17 15:32:11 +05:30
Sayak Paul
2d94c7838e
[Core] feat: enable fused attention projections for other SD and SDXL pipelines ( #6179 )
...
* feat: enable fused attention projections for other SD and SDXL pipelines
* add: test for SD fused projections.
2023-12-16 08:45:54 +05:30
Sayak Paul
a81334e3f0
[LoRA] add an error message when dealing with _best_guess_weight_name ofline ( #6184 )
...
* add an error message when dealing with _best_guess_weight_name ofline
* simplify condition
2023-12-16 08:36:08 +05:30
Dhruv Nair
d704a730cd
Compile test fix ( #6104 )
...
* update
* update
2023-12-15 18:34:46 +05:30
dg845
49db233b35
Clean Up Comments in LCM(-LoRA) Distillation Scripts. ( #6145 )
...
* Clean up comments in LCM(-LoRA) distillation scripts.
* Calculate predicted source noise noise_pred correctly for all prediction_types.
* make style
* apply suggestions from review
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-15 18:18:16 +05:30
Dhruv Nair
93ea26f272
Add PEFT to training deps ( #6148 )
...
add peft to training deps
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-15 08:39:59 +05:30
Dhruv Nair
f5dfe2a8b0
LoRA test fixes ( #6163 )
...
* update
* update
* update
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-15 08:39:41 +05:30
Patrick von Platen
4836cfad98
[Sigmas] Keep sigmas on CPU ( #6173 )
...
* correct
* Apply suggestions from code review
* make style
2023-12-15 07:43:18 +05:30
Kuba
1ccbfbb663
[docs] Add missing \ in lora.md ( #6174 )
2023-12-14 16:55:43 -08:00
Linoy Tsaban
29dfe22a8e
[advanced dreambooth lora sdxl training script] load pipeline for inference only if validation prompt is used ( #6171 )
...
* load pipeline for inference only if validation prompt is used
* move things outside
* load pipeline for inference only if validation prompt is used
* fix readme when validation prompt is used
---------
Co-authored-by: linoytsaban <linoy@huggingface.co >
Co-authored-by: apolinário <joaopaulo.passos@gmail.com >
2023-12-14 11:45:33 -06:00
Aryan V S
56806cdbfd
Add missing subclass docs, Fix broken example in SD_safe ( #6116 )
...
* fix broken example in pipeline_stable_diffusion_safe
* fix typo in pipeline_stable_diffusion_pix2pix_zero
* add missing docs
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-14 09:20:30 -08:00
Steven Liu
8ccc76ab37
[docs] IP-Adapter API doc ( #6140 )
...
add ip-adapter
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-14 09:19:37 -08:00
Monohydroxides
c46711e895
[Community] Add SDE Drag pipeline ( #6105 )
...
* Add community pipeline: sde_drag.py
* Update README.md
* Update README.md
Update example code and visual example
* Update sde_drag.py
Update code example.
2023-12-14 20:47:20 +05:30
Sayak Paul
1d686bac81
[feat: Benchmarking Workflow] add stuff for a benchmarking workflow ( #5839 )
...
* add poc for benchmarking workflow.
* import
* fix argument
* fix: argument
* fix: path
* fix
* fix
* path
* output csv files.
* workflow cleanup
* append token
* add utility to push to hf dataset
* fix: kw arg
* better reporting
* fix: headers
* better formatting of the numbers.
* better type annotation
* fix: formatting
* moentarily disable check
* push results.
* remove disable check
* introduce base classes.
* img2img class
* add inpainting pipeline
* intoduce base benchmark class.
* add img2img and inpainting
* feat: utility to compare changes
* fix
* fix import
* add args
* basepath
* better exception handling
* better path handling
* fix
* fix
* remove
* ifx
* fix
* add: support for controlnet.
* image_url -> url
* move images to huggingface hub
* correct urls.
* root_ckpt
* flush before benchmarking
* don't install accelerate from source
* add runner
* simplify Diffusers Benchmarking step
* change runner
* fix: subprocess call.
* filter percentage values
* fix controlnet benchmark
* add t2i adapters.
* fix filter columns
* fix t2i adapter benchmark
* fix init.
* fix
* remove safetensors flag
* fix args print
* fix
* feat: run_command
* add adapter resolution mapping
* benchmark t2i adapter fix.
* fix adapter input
* fix
* convert to L.
* add flush() add appropriate places
* better filtering
* okay
* get env for torch
* convert to float
* fix
* filter out nans.
* better coment
* sdxl
* sdxl for other benchmarks.
* fix: condition
* fix: condition for inpainting
* fix: mapping for resolution
* fix
* include kandinsky and wuerstchen
* fix: Wuerstchen
* Empty-Commit
* [Community] AnimateDiff + Controlnet Pipeline (#5928 )
* begin work on animatediff + controlnet pipeline
* complete todos, uncomment multicontrolnet, input checks
Co-Authored-By: EdoardoBotta <botta.edoardo@gmail.com >
* update
Co-Authored-By: EdoardoBotta <botta.edoardo@gmail.com >
* add example
* update community README
* Update examples/community/README.md
---------
Co-authored-by: EdoardoBotta <botta.edoardo@gmail.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* EulerDiscreteScheduler add `rescale_betas_zero_snr` (#6024 )
* EulerDiscreteScheduler add `rescale_betas_zero_snr`
* Revert "[Community] AnimateDiff + Controlnet Pipeline (#5928 )"
This reverts commit 821726d7c0#6024 )"
This reverts commit 3dc2362b5apatrick.v.platen@gmail.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
Co-authored-by: Aryan V S <contact.aryanvs@gmail.com >
Co-authored-by: EdoardoBotta <botta.edoardo@gmail.com >
Co-authored-by: Beinsezii <39478211+Beinsezii@users.noreply.github.com >
2023-12-12 11:03:34 +05:30
M. Tolga Cangöz
0a401b95b7
[Docs] Fix typos ( #6122 )
...
Fix typos and trim trailing whitespaces
2023-12-11 10:55:28 -08:00
Edward Li
664e931bcb
Correct type annotation for VaeImageProcessor.numpy_to_pil ( #6111 )
...
From `(np.ndarray) -> PIL.Image.Image` to `(np.ndarray) -> List[PIL.Image.Image]`.
2023-12-11 15:22:04 +05:30
Aryan V S
88bdd97ccd
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 >
2023-12-10 21:19:14 +05:30
Charchit Sharma
08b453e382
IP-Adapter for StableDiffusionControlNetImg2ImgPipeline ( #5901 )
...
* adapter for StableDiffusionControlNetImg2ImgPipeline
* fix-copies
* fix-copies
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-12-09 11:02:55 +05:30
apolinário
2a111bc9fe
[Advanced Training Script] Fix pipe example ( #6106 )
2023-12-08 15:56:35 +01:00
apolinário
16e6997f0d
[Advanced Diffusion Script] Add Widget default text ( #6100 )
...
add widget
2023-12-08 12:45:27 +01:00
