1
0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Commit Graph

2176 Commits

Author SHA1 Message Date
mengfei25
7b6caca9eb Modify example with intel optimization (#2896)
* modify intel opts inference script

* modify readme

* modify doc

* fix some issues

* reformat

* reformat script

* format issue

* format issue
2023-03-31 13:07:20 +01:00
Sandeep
f3fbf9bfc0 Fix check_inputs in upscaler pipeline to allow embeds (#2892)
* Remove suggestion to use cuDNN benchmark in docs

* removing the wrong line

* add support for embeds

* fix line length
2023-03-31 12:46:20 +01:00
Patrick von Platen
e1144ac20c Fix slow tests text inv (#2915)
* fix slow tests

* uP
2023-03-31 10:03:32 +01:00
Guillermo Cique
1055175a18 Fix textual inversion loading (#2914) 2023-03-31 09:52:48 +01:00
Takuma Mori
0df4ad541f Add support Karras sigmas for StableDiffusionKDiffusionPipeline (#2874)
* add use_karras_sigmas option

thanks @Stax124

* fix sigma_min/max from scheduler.sigmas

* add docstring

* revert to use k_diffusion_model.sigma, to(device)

* add integration test

* make style
2023-03-31 09:12:11 +05:30
YiYi Xu
51d970d60d [docs] add the Stable diffusion with Jax/Flax Guide into the docs (#2487)
* add stable diffusion jax guide


---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-30 16:22:40 -10:00
Pi Esposito
a937e1b594 add load textual inversion embeddings to stable diffusion (#2009)
* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add case for parsing embedding from auto1111 UI format

Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>

* fix style after rebase

* move textual inversion mixin to loaders

* move mixin inheritance to DiffusionPipeline from StableDiffusionPipeline)

* update dummy class name

* addressed allo comments

* fix old dangling import

* fix style

* proposal

* remove bogus

* Apply suggestions from code review

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

* finish

* make style

* up

* fix code quality

* fix code quality - again

* fix code quality - 3

* fix alt diffusion code quality

* fix model editing pipeline

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Finish

---------

Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
2023-03-30 18:08:39 +01:00
Michael Gartsbein
1d033a95f6 img2img.multiple.controlnets.pipeline (#2833)
* img2img.multiple.controlnets.pipeline

* remove comments

---------

Co-authored-by: mishka <gartsocial@gmail.com>
2023-03-30 18:00:12 +01:00
Patrick von Platen
49609768b4 make style 2023-03-30 18:26:41 +02:00
Alon Burg
9062b2847d Support fp16 in conversion from original ckpt (#2733)
add --half to convert_original_stable_diffusion_to_diffusers.py
2023-03-30 17:26:18 +01:00
YiYi Xu
b3d5cc4a36 add flax requirement (#2894)
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-03-30 17:10:26 +01:00
Sayak Paul
b2021273eb [Docs] add an example use for StableUnCLIPPipeline in the pipeline docs (#2897)
* improve stable unclip doc.

* add: entry of StableUnCLIPPipeline to the docs

* Apply suggestions from code review

Co-authored-by: apolinario <joaopaulo.passos@gmail.com>

---------

Co-authored-by: apolinario <joaopaulo.passos@gmail.com>
2023-03-30 17:14:04 +05:30
Steven Liu
e47459c80f [docs] Performance tutorial (#2773)
* update performance tutorial

* fix divs

* oops forgot to close tag

* apply feedback

* apply feedback

* apply feedback

* align doc title
2023-03-29 12:48:14 -07:00
Yaman Ahlawat
3be489182e feat: allow offset_noise in dreambooth training example (#2826) 2023-03-29 16:01:02 +05:30
Sayak Paul
d82b032319 [Examples] Add streaming support to the ControlNet training example in JAX (#2859)
* improve stable unclip doc.

* feat: add streaming support to controlnet flax training script.

* fix: CLI arg.

* fix: torch dataloader shuffle setting.

* fix: dataset length.

* fix: wandb config.

* fix: steps_per_epoch in the training loop.

* add: entry about streaming in the readme

* get column names from iterable dataset + fix final logging

---------

Co-authored-by: yiyixuxu <yixu310@gmail.com>
2023-03-29 06:42:08 +05:30
Patrick von Platen
40a7b8629e [Docs] Correct phrasing (#2873) 2023-03-28 17:32:18 +01:00
M. Tolga Cangöz
628fefb232 Update stable_diffusion_safe.mdx (#2870)
Fix typos
2023-03-28 17:23:54 +01:00
M. Tolga Cangöz
03fe36f183 Update paint_by_example.mdx (#2869)
.
2023-03-28 17:23:39 +01:00
M. Tolga Cangöz
ef4c2fa4f1 Update alt_diffusion.mdx (#2865)
Fix typos
2023-03-28 17:17:53 +01:00
M. Tolga Cangöz
3980858ad4 Update overview.mdx (#2864)
Fix typos
2023-03-28 17:17:33 +01:00
M. Tolga Cangöz
37c82480bb Update evaluation.mdx (#2862)
Fix typos
2023-03-28 17:15:37 +01:00
Sayak Paul
13845462db [Tests] Adds a test to check if image_embeds None case is handled properly in StableUnCLIPImg2ImgPipeline (#2861)
* improve stable unclip doc.

* add: test to check if image_emebds None case is handled.

* apply formatting/
2023-03-28 17:14:08 +01:00
Nipun Jindal
53377ef83c [2761]: Add documentation for extra_in_channels UNet1DModel (#2817)
Co-authored-by: njindal <njindal@adobe.com>
2023-03-28 16:56:45 +01:00
dg845
4d0f412d0d [WIP] Check UNet shapes in StableDiffusionInpaintPipeline __init__ (#2853)
Add warning in __init__ if user loads a checkpoint with pipeline.unet.config.in_channels other than 9.
2023-03-28 16:53:52 +01:00
Felix Blanke
25d927aa51 Add last_epoch argument to optimization.get_scheduler (#2850)
Add last_epoch arg to optimization.get_scheduler.

Allows the specification of the index of the last epoch when
resuming training.
2023-03-28 16:46:41 +01:00
dg845
663c654577 [WIP][Docs] Use DiffusionPipeline Instead of Child Classes when Loading Pipeline (#2809)
* Change the docs to use the parent DiffusionPipeline class when loading a checkpoint using from_pretrained() instead of a child class (e.g. StableDiffusionPipeline) where possible.

* Run make style to fix style issues.

* Change more docs to use DiffusionPipeline rather than a subclass.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-28 16:44:34 +01:00
John HU
920a15cf70 Fix link to LoRA training guide in DreamBooth training guide (#2836)
Fix link to LoRA training guide
2023-03-28 16:35:41 +01:00
cmdr2
7d756813d4 Update the legacy inpainting SD pipeline, to allow calling it with only prompt_embeds (instead of always requiring a prompt) (#2842)
Fix error 'required positional argument: prompt' when Legacy Inpaint is called only with prompt_embeds
2023-03-28 16:30:49 +01:00
Li-Huai (Allan) Lin
159a0bff34 Remove duplicate sentence in docstrings (#2834)
* Remove duplicate sentence

* format
2023-03-28 16:27:51 +01:00
Sandeep
b76d9fde8d Remove suggestion to use cuDNN benchmark in docs (#2793)
* Remove suggestion to use cuDNN benchmark in docs

* removing the wrong line
2023-03-28 16:01:30 +01:00
Aki Sakurai
0f14335af3 StableDiffusionLongPromptWeightingPipeline: Do not hardcode pad token (#2832) 2023-03-28 16:00:56 +01:00
junhsss
8bdf423645 fix KarrasVePipeline bug (#2828) 2023-03-28 15:58:19 +01:00
Stax124
585f621af2 [Stable Diffusion] Allow users to disable Safety checker if loading model from checkpoint (#2768)
* Allow user to disable SafetyChecker and enable dtypes if loading models from .ckpt or .safetensors

* Fix Import sorting (Ruff error)

* Get rid of the dtype convert method as it was implemented all along

* Fix the docstring

* Fix ruff formatting

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-28 15:06:48 +01:00
Kashif Rasul
c0afca2d12 updated onnx pndm test (#2811) 2023-03-28 13:43:24 +01:00
Patrick von Platen
42d950174f [Init] Make sure shape mismatches are caught early (#2847)
Improve init
2023-03-28 09:08:28 +01:00
Pedro Cuenca
81125d8499 Make dynamo wrapped modules work with save_pretrained (#2726)
* Workaround for saving dynamo-wrapped models.

* Accept suggestion from code review

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

* Apply workaround when overriding pipeline components.

* Ensure the correct config.json is saved to disk.

Instead of the dynamo class.

* Save correct module (not compiled one)

* Add test

* style

* fix docstrings

* Go back to using string comparisons.

PyTorch CPU does not have _dynamo.

* Simple test for save_pretrained of compiled models.

* Helper function to test whether module is compiled.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-28 09:03:21 +02:00
YiYi Xu
d4f846fa74 [WIP]Flax training script for controlnet (#2818)
* add train_controlnet_flax

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-27 19:13:35 -10:00
Sayak Paul
58fc824488 add: better warning messages when handling multiple conditionings. (#2804)
* add: better warning messages when handling multiple conditioning.

* fix: handling of controlnet_conditioning_scale
2023-03-28 08:19:39 +05:30
Sayak Paul
fab4f3d6e4 improve stable unclip doc. (#2823) 2023-03-28 08:18:29 +05:30
Pedro Cuenca
b10f527577 Helper function to disable custom attention processors (#2791)
* Helper function to disable custom attention processors.

* Restore code deleted by mistake.

* Format

* Fix modeling_text_unet copy.
2023-03-27 20:31:19 +02:00
Eugene Lyapustin
7bc2fff1a5 Fix StableUnCLIPImg2ImgPipeline handling of explicitly passed image embeddings (#2845) 2023-03-27 19:03:59 +01:00
Patrick von Platen
4c26cb9cc8 [Tests] Fix slow tests (#2846) 2023-03-27 18:45:49 +01:00
Pedro Cuenca
1d7b4b60b7 Ruff: apply same rules as in transformers (#2827)
* Apply same ruff settings as in transformers

See https://github.com/huggingface/transformers/blob/main/pyproject.toml
Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* Apply new style rules

* Style

Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* style

* remove list, ruff wouldn't auto fix.

---------

Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>
2023-03-27 16:18:57 +02:00
Sayak Paul
abb22b4eeb Update examples README.md to include the latest examples (#2839) 2023-03-27 19:34:58 +05:30
Bahjat Kawar
9fb0217548 StableDiffusionModelEditingPipeline documentation (#2810)
* comment update

* comment update
2023-03-24 22:41:31 +05:30
Sayak Paul
5883d8d4d1 [Docs] update docs (Stable unCLIP) to reflect the updated ckpts. (#2815)
* update docs to reflect the updated ckpts.

* update: point about prompt.

* Apply suggestions from code review

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

* emove image resizing.

* Apply suggestions from code review

* Apply suggestions from code review

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2023-03-24 17:24:19 +01:00
Patrick von Platen
dbcb15c25f [Stable UnCLIP] Finish Stable UnCLIP (#2814)
* up

* fix more 7

* up

* finish
2023-03-24 17:04:41 +01:00
PeixuanZuo
c4892f1855 Update onnxruntime package candidates (#2666)
* update import onnxruntime package, enable onnxruntime-rocm and onnxruntime-training

* add ort_nightly_gpu
2023-03-24 12:23:05 +01:00
Kashif Rasul
f6feb69991 Relax DiT test (#2808)
* Relax DiT test

* relax 2 more tests

* fix style

* skip test on mac due to older protobuf
2023-03-24 11:28:55 +01:00
Bahjat Kawar
37a44bb283 Add ModelEditing pipeline (#2721)
* TIME first commit

* styling.

* styling 2.

* fixes; tests

* apply styling and doc fix.

* remove sups.

* fixes

* remove temp file

* move augmentations to const

* added doc entry

* code quality

* customize augmentations

* quality

* quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
2023-03-24 13:01:39 +05:30