AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity
1,362 Commits 740 Branches 94 Tags
d50e3217459558cc2979f38818f1835751d4fc97
Commit Graph

1362 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Anton Lozhkov
d50e321745 Support SD2 attention slicing (#1397) 
* Support SD2 attention slicing

* Support SD2 attention slicing

* Add more copies

* Use attn_num_head_channels in blocks

* fix-copies

* Update tests

* fix imports
 2022-11-24 22:42:59 +01:00
Patrick von Platen
8e2c4cd56c Deprecate sample size (#1406) 
* up

* up

* fix

* uP

* more fixes

* up

* uP

* up

* up

* uP

* fix final tests
 2022-11-24 22:32:44 +01:00
Anton Lozhkov
bb2c64a08c Add the new SD2 attention params to the VD text unet (#1400) 2022-11-24 21:57:27 +01:00
Patrick von Platen
05a36d5c1a Upscaling fixed (#1402) 
* Upscaling fixed

* up

* more fixes

* fix

* more fixes

* finish again

* up
 2022-11-24 20:33:52 +01:00
Patrick von Platen
cbfed0c256 [Config] Add optional arguments (#1395) 
* Optional Components

* uP

* finish

* finish

* finish

* Apply suggestions from code review

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

* up

* Update src/diffusers/pipeline_utils.py

* improve

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-24 20:05:41 +01:00
Patrick von Platen
e0e86b7470 Make height and width optional (#1401) 
* fix

* add test

* fix test

* uP

* up

* fix some tests
 2022-11-24 18:23:59 +01:00
Anton Lozhkov
81d8f4a9e1 Version 0.9.0.dev0 (#1394) 2022-11-24 14:54:29 +01:00
Suraj Patil
cecdd8bdd1 Adapt UNet2D for supre-resolution (#1385) 
* allow disabling self attention

* add class_embedding

* fix copies

* fix condition

* fix copies

* do_self_attention -> only_cross_attention

* fix copies

* num_classes -> num_class_embeds

* fix default value
 2022-11-24 14:49:03 +01:00
Suraj Patil
30f6f44104 add v prediction (#1386) 
* add v prediction

* adat euler for v pred

* velocity -> v_prediction

* simplify

* fix naming

* Update src/diffusers/schedulers/scheduling_euler_discrete.py

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

* style

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-24 12:25:19 +01:00
Patrick von Platen
9f476388fa trailing . fix 2022-11-24 00:53:57 +01:00
Patrick von Platen
9479052dde fix trailing . dep object 2022-11-24 00:33:32 +01:00
Patrick von Platen
35d8186172 [Bad dependencies] Fix imports (#1382) 
* fix imports

* better error

* up

* finish
 2022-11-24 00:24:05 +01:00
Suraj Patil
1524122532 [Transformer2DModel] don't norm twice (#1381) 
don't norm twice
 2022-11-24 00:12:45 +01:00
Suraj Patil
f07a16e09b update unet2d (#1376) 
* boom boom

* remove duplicate arg

* add use_linear_proj arg

* fix copies

* style

* add fast tests

* use_linear_proj -> use_linear_projection
 2022-11-23 20:46:30 +01:00
anton-l
16a32c9dab Release: v0.8.0 v0.8.0 2022-11-23 19:12:31 +01:00
Patrick von Platen
2625fb59dc [Versatile Diffusion] Add versatile diffusion model (#1283) 
* up

* convert dual unet

* revert dual attn

* adapt for vd-official

* test the full pipeline

* mixed inference

* mixed inference for text2img

* add image prompting

* fix clip norm

* split text2img and img2img

* fix format

* refactor text2img

* mega pipeline

* add optimus

* refactor image var

* wip text_unet

* text unet end to end

* update tests

* reshape

* fix image to text

* add some first docs

* dual guided pipeline

* fix token ratio

* propose change

* dual transformer as a native module

* DualTransformer(nn.Module)

* DualTransformer(nn.Module)

* correct unconditional image

* save-load with mega pipeline

* remove image to text

* up

* uP

* fix

* up

* final fix

* remove_unused_weights

* test updates

* save progress

* uP

* fix dual prompts

* some fixes

* finish

* style

* finish renaming

* up

* fix

* fix

* fix

* finish

Co-authored-by: anton-l <anton@huggingface.co>
 2022-11-23 19:03:45 +01:00
Suraj Patil
0eb507f2af StableDiffusionImageVariationPipeline (#1365) 
* add StableDiffusionImageVariationPipeline

* add ini init

* use CLIPVisionModelWithProjection

* fix _encode_image

* add copied from

* fix copies

* add doc

* handle tensor in _encode_image

* add tests

* correct model_id

* remove copied from in enable_sequential_cpu_offload

* fix tests

* make slow tests pass

* update slow tests

* use temp model for now

* fix test_stable_diffusion_img_variation_intermediate_state

* fix test_stable_diffusion_img_variation_intermediate_state

* check for torch.Tensor

* quality

* fix name

* fix slow tests

* install transformers from source

* fix install

* fix install

* Apply suggestions from code review

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

* input_image -> image

* remove deprication warnings

* fix test_stable_diffusion_img_variation_multiple_images

* make flake happy

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-23 14:36:39 +01:00
Suraj Patil
9e234d8048 handle fp16 in UNet2DModel (#1216) 
* make sure fp16 runs well

* add fp16 test for superes

* Update src/diffusers/models/unet_2d.py

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

* gen on cuda

* always run fast inferecne test on cpu

* run on cpu

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-23 11:13:34 +01:00
Penn
8fd3a74322 Fix using non-square images with UNet2DModel and DDIM/DDPM pipelines (#1289) 
* fix non square images with UNet2DModel and DDIM/DDPM pipelines

* fix unet_2d `sample_size` docstring

* update pipeline tests for unet uncond

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-11-23 11:11:39 +01:00
regisss
44e56de9aa Replace logger.warn by logger.warning (#1366) 2022-11-22 20:44:34 +01:00
Suraj Patil
2d6d4edbbd use memory_efficient_attention by default (#1354) 
* use memory_efficient_attention by default

* Update src/diffusers/models/attention.py

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-22 13:37:17 +01:00
Suraj Patil
8b84f85192 [examples] fix mixed_precision arg (#1359) 
* use accelerator to check mixed_precision

* default `mixed_precision` to `None`

* pass mixed_precision to accelerate launch
 2022-11-22 13:35:23 +01:00
Manuel Brack
e50c25d808 Add Safe Stable Diffusion Pipeline (#1244) 
* Add pipeline_stable_diffusion_safe.py to pipelines

* Fix repository consistency

Ran make fix-copies after adding new pipline

* Add Paper/Equation reference for parameters to doc string

* Ensure code style and quality

* Perform code refactoring

* Fix copies inherited from merge with huggingface/main

* Add docs

* Fix code style

* Fix errors in documentation

* Fix refactoring error

* remove debugging print statement

* added Safe Latent Diffusion tests

* Fix style

* Fix style

* Add pre-defined safety configurations

* Fix line-break

* fix some tests

* finish

* Change safety checker

* Add missing safety_checker.py file

* Remove unused imports

Co-authored-by: PatrickSchrML <patrick_schramowski@hotmail.de>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-11-22 11:51:30 +01:00
Patrick von Platen
182eb959e5 [Community Pipelines] K-Diffusion Pipeline (#1360) 
* up

* add readme

* up

* uP
 2022-11-21 18:45:50 +01:00
Birch-san
ad93593345 perf: prefer batched matmuls for attention (#1203) 
perf: prefer batched matmuls for attention. added fast-path to Decoder when num_heads=1
 2022-11-21 15:01:11 +01:00
Stuti R
78a6eed2d7 Add bit diffusion [WIP] (#971) 
* Create bit_diffusion.py

Bit diffusion based on the paper, arXiv:2208.04202, Chen2022AnalogBG

* adding bit diffusion to new branch

ran tests

* tests

* tests

* tests

* tests

* removed test folders + added to README

* Update README.md

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-11-21 11:50:32 +01:00
shunxing1234
94b27fb8da change the sample model (#1352) 
* Update alt_diffusion.mdx

* Update alt_diffusion.mdx
 2022-11-21 11:28:25 +01:00
Patrick von Platen
ab1f01e634 make style 2022-11-20 19:37:28 +01:00
Patrick von Platen
2b31740d54 Merge branch 'main' of https://github.com/huggingface/diffusers 2022-11-20 19:37:14 +01:00
Victor Schmidt
3bec90ff2c Handle batches and Tensors in pipeline_stable_diffusion_inpaint.py:prepare_mask_and_masked_image (#1003) 
* Handle batches and Tensors in `prepare_mask_and_masked_image`

* `blackfy`
upgrade `black`

* handle mask as `np.array`

* add docstring

* revert `black` changes with smaller line length

* missing ValueError in docstring

* raise `TypeError` for image as tensor but not mask

* typo in mask shape selection

* check for batch dim

* fix: wrong indentation

* add tests

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-11-20 19:33:09 +01:00
Ki
eb2425b88c Update README.md: Minor change to Imagic code snippet, missing dir error (#1347) 
Minor change to Imagic Readme

Missing dir causes an error when running the example code.
 2022-11-20 18:59:56 +01:00
Ki
44efcbda0a Update README.md: IMAGIC example code snippet misspelling (#1346) 
Update README.md

Minor spelling mistake.
 2022-11-20 18:56:57 +01:00
Juan Acevedo
7bbbfbfd18 Jax infer support negative prompt (#1337) 
* support negative prompts in sd jax pipeline

* pass batched neg_prompt

* only encode when negative prompt is None

Co-authored-by: Juan Acevedo <jfacevedo@google.com>
 2022-11-19 20:51:52 +01:00
Clayton Sims
30220905c4 Legacy Inpainting Pipeline for Onnx Models (#1237) 
* Add legacy inpainting pipeline compatibility for onnx

* remove commented out line

* Add onnx legacy inpainting test

* Fix slow decorators

* pep8 styling

* isort styling

* dummy object

* ordering consistency

* style

* docstring styles

* Refactor common prompt encoding pattern

* Update tests to permanent repository home

* support all available schedulers until ONNX IO binding is available

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* updated styling from PR suggested feedback

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
 2022-11-18 16:33:12 +01:00
Anton Lozhkov
7240318179 Fix the order of casts for onnx inpainting (#1338) 2022-11-18 16:30:07 +01:00
NotNANtoN
aa2ce41b99 Fix img2img speed with LMS-Discrete Scheduler (#896) 
Casting `self.sigmas` into a different dtype (the one of original_samples) is not advisable. In my img2img pipeline this leads to a long running time in the  `integrate.quad` call later on- by long I mean more than 10x slower.

Co-authored-by: Anton Lozhkov <anton@huggingface.co>
 2022-11-18 16:01:57 +01:00
Anton Lozhkov
81fa2d688d Avoid nested fix-copies (#1332) 
* Avoid nested `# Copied from` statements during `make fix-copies`

* style
 2022-11-18 15:33:57 +01:00
Patrick von Platen
195e437ac5 Correct path to schedlure (#1322) 
* [Examples] Correct path

* uP
 2022-11-18 12:32:49 +01:00
Patrick von Platen
fcfdd95f0b Fix/Enable all schedulers for in-painting (#1331) 
* inpaint fix k lms

* onnox as well

* up
 2022-11-18 12:32:17 +01:00
Simon Kirsten
5dcef138bf [Flax] Fix loading scheduler from subfolder (#1319) 
[FLAX] Fix loading scheduler from subfolder
 2022-11-18 11:31:07 +01:00
Nathan Lambert
0cfbb51b0c add docs for multi-modal examples (#1227) 
* add docs for multi-modal

* many changes

* fix docs build

* fix links

* Update docs/source/using-diffusers/other-modalities.mdx

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

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-11-17 10:25:49 -08:00
Patrick von Platen
b9b7039f0e img2text Typo (#1329) 
* make fix copies again

* Fix typo
 2022-11-17 16:48:15 +01:00
Patrick von Platen
63b34191b9 Fix typo 2022-11-17 16:47:19 +01:00
Patrick von Platen
b21a463aa9 rg Merge branch 'main' of https://github.com/huggingface/diffusers 2022-11-17 16:46:33 +01:00
Anton Lozhkov
e05ca84f41 [ONNX] Support Euler schedulers (#1328) 2022-11-17 16:37:35 +01:00
Patrick von Platen
3b48620f5e Merge branch 'main' of https://github.com/huggingface/diffusers 2022-11-17 16:14:53 +01:00
Patrick von Platen
632dacea2f [Custom pipeline] Easier loading of local pipelines (#1327) 
* [Custom pipeline] Easier loading of local pipelines

* upgrade black
 2022-11-17 16:00:26 +01:00
Patrick von Platen
3fb28c44a3 xMerge branch 'main' of https://github.com/huggingface/diffusers 2022-11-17 15:50:36 +01:00
Patrick von Platen
2dd12e38af make fix copies again 2022-11-17 15:50:33 +01:00
Prathik Rao
3346ec3acd integrate ort (#1110) 
* integrate ort

* use return_dict=False

* revert unet return value change

* revert unet return value change

* add note to readme

* adjust readme

* add contact

* `make style`

Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
 2022-11-17 15:48:41 +01:00