Mirrors
/
diffusers
mirror of https://github.com/ShivamShrirao/diffusers.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,127 Commits 2 Branches 0 Tags 24 MiB
Commit Graph

1127 Commits

Author SHA1 Message Date
Anton Lozhkov cc36f2e7ff
Bump the version to 0.7.0.dev0 (#912) 
* Bump the version to 0.7.0.dev0

* deprecate offsets

* deprecate LMS timesteps

* LMS 0.7.0->0.8.0
 2022-10-20 20:25:20 +02:00
SkyTNT ba74a8be7a
[Community Pipelines] Fix pad_tokens_and_weights in lpw_stable_diffusion (#925) 
[Community Pipelines] fix pad_tokens_and_weights in lpw_stable_diffusion
 2022-10-20 19:26:04 +02:00
Krishna Penukonda 6f6eef747c
Fix Compatibility with Nvidia NGC Containers (#919) 
Check if MPS backend is registered before calling is_available()
 2022-10-20 19:23:42 +02:00
Suraj Patil 8be48507a0
fix test_components (#928) 2022-10-20 16:25:12 +02:00
Hanusz Leszek 4bf675f465
Dreambooth class image generation: using unique names to avoid overwriting existing image (#847) 
* Add an underscore to filename if it already exists

* Use sha1sum hash instead of adding underscores
 2022-10-20 15:56:15 +02:00
Suraj Patil 7674a36a34
[dreambooth] dont use safety check when generating prior images (#922) 
dont' use safety check when generating prior images
 2022-10-20 13:52:11 +02:00
Mikail Duzenli a5eb7f4293
[Examples] add speech to image pipeline example (#897) 
* First draft

* created the SpeechToImagePipeline class

* Corrected speech_to_image_diffusion.py style

* Added safety checker

* Corrected style

* Adding examples to README
 2022-10-20 13:47:13 +02:00
Hanusz Leszek ce7d96681c
DOC Dreambooth Add --sample_batch_size=1 to the 8 GB dreambooth example script (#829) 
Add --sample_batch_size=1 to the 8 GB dreambooth script
 2022-10-20 13:44:37 +02:00
Patrick von Platen db19a9d9d7
[DiffusionPipeline.from_pretrained] add warning when passing unused k… (#870) 
[DiffusionPipeline.from_pretrained] add warning when passing unused kwargs
 2022-10-20 13:30:01 +02:00
Patrick von Platen 4a76e5d49b
[PNDM Scheduler] Make sure list cannot grow forever (#882) 2022-10-20 13:29:04 +02:00
Patrick von Platen 83f8a5ff70
[Stable Diffusion] Add components function (#889) 
* [Stable Diffusion] Add components function

* uP
 2022-10-20 13:28:11 +02:00
SkyTNT 2a0c823527
[Community Pipelines] Long Prompt Weighting Stable Diffusion Pipelines (#907) 
* [Community Pipelines] Long Prompt Weighting

* Update README.md

* fix

* style

* fix style

* Update examples/community/README.md

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-19 22:30:46 +02:00
anton-l ad9d7ce476 Release: 0.6.0 2022-10-19 17:38:55 +02:00
Pedro Cuenca 8124863d1f
Initial docs update for new in-painting pipeline (#910) 
Docs update for new in-painting pipeline.

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-19 17:31:23 +02:00
Anton Lozhkov 89d124945a
ONNX supervised inpainting (#906) 
* ONNX supervised inpainting

* sync with the torch pipeline

* fix concat

* update ref values

* back to 8 steps

* type fix

* make fix-copies
 2022-10-19 17:03:31 +02:00
Patrick von Platen 46557121e6
finish tests (#909) 2022-10-19 16:36:51 +02:00
Suraj Patil b35d88c536
Stable diffusion inpainting. (#904) 
* begin pipe

* add new pipeline

* add tests

* correct fast test

* up

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

* Update tests/test_pipelines.py

* up

* up

* make style

* add fp16 test

* doc, comments

* up

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
 2022-10-19 16:11:50 +02:00
Patrick von Platen 83b696e6c0
[Communit Pipeline] Make sure "mega" uses correct inpaint pipeline (#908) 2022-10-19 15:54:07 +02:00
Patrick von Platen 6ea83608ad
[Stable Diffusion Inpainting] Deprecate inpainting pipeline in favor of official one (#903) 
* finish

* up

* Apply suggestions from code review

Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Update src/diffusers/pipeline_utils.py

* Finish

Co-authored-by: Anton Lozhkov <anton@huggingface.co>
 2022-10-19 12:55:37 +02:00
Patrick von Platen bd216073fe make fix copies 2022-10-19 12:31:53 +02:00
Anton Lozhkov 8eb9d9703d
Improve ONNX img2img numpy handling, temporarily fix the tests (#899) 
* [WIP] Onnx img2img determinism

* more numpy + seed

* numpy inpainting, tolerance

* revert test workflow
 2022-10-19 11:26:32 +02:00
Žilvinas Ledas a9908ecfc1
Stable Diffusion image-to-image and inpaint using onnx. (#552) 
* * Stabe Diffusion img2img using onnx.

* * Stabe Diffusion inpaint using onnx.

* Export vae_encoder, upgrade img2img, add test

* updated inpainting pipeline + test

* style

Co-authored-by: anton-l <anton@huggingface.co>
 2022-10-18 17:44:01 +02:00
Suraj Patil fbe807bf57
[dreambooth] allow fine-tuning text encoder (#883) 
* allow fine-tuning text encoder

* fix a few things

* update readme
 2022-10-18 17:28:51 +02:00
Hamish Friedlander a3efa433ea
Fix DDIM on Windows not using int64 for timesteps (#819) 2022-10-18 12:06:46 +02:00
Anton Lozhkov 728a3f3ec1
Rename StableDiffusionOnnxPipeline -> OnnxStableDiffusionPipeline (#887) 
Rename and deprecate
 2022-10-18 09:14:30 +02:00
Pedro Cuenca 100e094cc9
Fix autoencoder test (#886) 
Fix autoencoder test.
 2022-10-17 21:47:13 +02:00
Anton Lozhkov cca59ce3a2
Add Apple M1 tests (#796) 
* [CI] Add Apple M1 tests

* setup-python

* python build

* conda install

* remove branch

* only 3.8 is built for osx-arm

* try fetching prebuilt tokenizers

* use user cache

* update shells

* Reports and cleanup

* -> MPS

* Disable parallel tests

* Better naming

* investigate worker crash

* return xdist

* restart

* num_workers=2

* still crashing?

* faulthandler for segfaults

* faulthandler for segfaults

* remove restarts, stop on segfault

* torch version

* change installation order

* Use pre-RC version of PyTorch.

To be updated when it is released.

* Skip crashing test on MPS, add new one that works.

* Skip cuda tests in mps device.

* Actually use generator in test.

I think this was a typo.

* make style

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-10-17 20:27:30 +02:00
Nathan Raw 627ad6e8ea
Rename frame filename in interpolation community example (#881) 
🎨 rename frame filename
 2022-10-17 20:08:58 +02:00
apolinario fd26624f3b
Add generic inference example to community pipeline readme (#874) 
Update README.md
 2022-10-17 17:16:50 +02:00
Nathan Raw dff91ee9a9
Fix table in community README.md (#879) 
Update README.md
 2022-10-17 16:51:25 +02:00
Pedro Cuenca 4dce37432b
Fix training push_to_hub (unconditional image generation): models were not saved before pushing to hub (#868) 
Fix: models were not saved before pushing to hub.
 2022-10-17 15:28:56 +02:00
Patrick von Platen 52e8fdb8ae
Update README.md 2022-10-17 15:25:04 +02:00
Patrick von Platen ed6c61c6a0
Fix small community pipeline import bug and finish README (#869) 
* up

* Finish
 2022-10-17 15:07:48 +02:00
Patrick von Platen 146419f741
All in one Stable Diffusion Pipeline (#821) 
* uP

* correct

* make style

* small change
 2022-10-17 14:37:25 +02:00
Patrick von Platen ad0e9ac7f6
Update README.md 2022-10-17 14:21:44 +02:00
Nathan Raw ee9875ee9b
Add Stable Diffusion Interpolation Example (#862) 
* ✨ Add Stable Diffusion Interpolation Example

* 💄 style

* Update examples/community/interpolate_stable_diffusion.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-17 13:48:42 +02:00
Patrick von Platen 5b94450ec3
Update README.md 2022-10-17 13:41:13 +02:00
Patrick von Platen 765a446dee
Update README.md 2022-10-17 13:34:15 +02:00
Patrick von Platen 2b7d4a5c21
[DeviceMap] Make sure stable diffusion can be loaded from older trans… (#860) 
[DeviceMap] Make sure stable diffusion can be loaded from older transformers versiosn
 2022-10-17 00:52:17 +02:00
camenduru 93a81a3f5a
Fix Flax pipeline: width and height are ignored #838 (#848) 
* Fix Flax pipeline: width and height are ignored #838

* Fix Flax pipeline: width and height are ignored
 2022-10-14 21:43:56 +02:00
Anton Lozhkov 1d3234cbca
Remove the last of ["sample"] (#842) 2022-10-14 14:45:43 +02:00
Anton Lozhkov 52394b53e2
Bump to 0.6.0.dev0 (#831) 
* Bump to 0.6.0.dev0

* Deprecate tensor_format and .samples

* style

* upd

* upd

* style

* sample -> images

* Update src/diffusers/schedulers/scheduling_ddpm.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_ddim.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_karras_ve.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_lms_discrete.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_pndm.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_sde_ve.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/schedulers/scheduling_sde_vp.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-14 13:43:52 +02:00
Omar Sanseviero b8c4d5801c
Remove unneeded use_auth_token (#839) 2022-10-14 13:27:03 +02:00
Patrick von Platen d3eb3b35be
[Community] One step unet (#840) 2022-10-14 13:09:21 +02:00
Patrick von Platen e48ca0f0a2
Release 0 5 1 (#833) 
Patch Release: 0.5.1
 2022-10-13 21:17:03 +02:00
Suraj Patil effe9d66eb
[FlaxStableDiffusionPipeline] fix bug when nsfw is detected (#832) 
fix nsfw bug
 2022-10-13 21:05:17 +02:00
Anton Lozhkov 0679d09083
Release: 5.0.0 (#830) 2022-10-13 18:48:50 +02:00
Patrick von Platen 1d51224403
[Flax] Complete tests (#828) 2022-10-13 18:18:32 +02:00
Patrick von Platen 7c2262640b
Align PT and Flax API - allow loading checkpoint from PyTorch configs (#827) 
* up

* finish

* add more tests

* up

* up

* finish
 2022-10-13 17:43:06 +02:00
Pedro Cuenca 78db11dbf3
Flax safety checker (#825) 
* Remove set_format in Flax pipeline.

* Remove DummyChecker.

* Run safety_checker in pipeline.

* Don't pmap on every call.

We could have decorated `generate` with `pmap`, but I wanted to keep it
in case someone wants to invoke it in non-parallel mode.

* Remove commented line

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Replicate outside __call__, prepare for optional jitting.

* Remove unnecessary clipping.

As suggested by @kashif.

* Do not jit unless requested.

* Send all args to generate.

* make style

* Remove unused imports.

* Fix docstring.

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-13 17:01:47 +02:00