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
1,513 Commits 740 Branches 94 Tags
badddee0ef8282e07232dcd3990070e2d524f57c
Commit Graph

1513 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Pedro Cuenca
badddee0ef Add state checkpointing to other training scripts (#1687) 
* Add state checkpointing to other training scripts

* Fix first_epoch

* Apply suggestions from code review

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

* Update Dreambooth checkpoint help message.

* Dreambooth docs: checkpoints, inference from a checkpoint.

* make style

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-12-15 19:49:40 +01:00
Anton Lozhkov
13994b2d3f RePaint fast tests and API conforming (#1701) 
* add fast tests

* better tests and fp16

* batch fixes

* Reuse preprocessing

* quickfix
 2022-12-15 18:35:31 +01:00
anton-
ea90bf2ba1 skip mps 2022-12-15 18:01:39 +01:00
Chino
8cecc66a74 Fix the bug that torch version less than 1.12 throws TypeError (#1671) 2022-12-14 21:29:39 +01:00
Anton Lozhkov
35b66c8e32 [Readme] Clarify package owners (#1707) 
Specify that we don't actively monitor the conda scripts
 2022-12-14 20:49:36 +01:00
Patrick von Platen
013edb641a Update main docs (#1706) 
* Remove bogus file

* [Docs] Remove mentioning of gated access since no longer exsits

* add docs to index

* Apply suggestions from code review

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

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-12-14 20:33:54 +01:00
Anton Lozhkov
86ac3ea1d7 Delete _ 2022-12-14 13:52:29 +01:00
Anton Lozhkov
ef3fcbb688 Remove all local telemetry (#1702) 2022-12-14 12:56:35 +01:00
Prathik Rao
7c823c2ed7 manually update train_unconditional_ort (#1694) 
* manually update train_unconditional_ort

* formatting

Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
 2022-12-14 11:35:41 +01:00
Pedro Cuenca
784beee969 Dreambooth: use warnings instead of logger in parse_args() (#1688) 
Use warnings instead of logger in parse_args()

logger requires an `Accelerator`.
 2022-12-13 22:01:48 +01:00
Patrick von Platen
8b7cb962a5 make style 2022-12-13 17:01:18 +00:00
Patrick von Platen
e1bb8f6188 [Community pipeline] Add github mechanism (#1680) 
* [Community pipeline] Add github mechanism

* better

* Apply suggestions from code review

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

* adapt

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-12-13 18:01:00 +01:00
Patrick von Platen
e62dd5cfa8 Change one-step dummy pipeline for testing (#1690) 
Change the one-step dummy pipeline for testing
 2022-12-13 16:55:49 +01:00
w4ffl35
07f95503e5 Disable telemetry when DISABLE_TELEMETRY is set (#1686) 
fixed #1685 - disables telemetry when DISABLE_TELEMETRY and HF_HUB_OFFLINE is set
 2022-12-13 16:28:07 +01:00
Pedro Cuenca
e01d6cf295 Dreambooth: save / restore training state (#1668) 
* Dreambooth: save / restore training state.

* make style

* Rename vars for clarity.

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

* Remove unused import

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-12-13 15:16:44 +01:00
Patrick von Platen
244e16a7ab [Version] Bump to 0.11.0.dev0 (#1682) 
upgrade version
 2022-12-13 13:51:36 +01:00
Patrick von Platen
b345c74d4d Make sure all pipelines can run with batched input (#1669) 
* [SD] Make sure batched input works correctly

* uP

* uP

* up

* up

* uP

* up

* fix mask stuff

* up

* uP

* more up

* up

* uP

* up

* finish

* Apply suggestions from code review

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

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-12-13 12:50:15 +01:00
apolinario
b417042291 Fix wrong type checking in convert_diffusers_to_original_stable_diffusion.py (#1681) 
* Fix type checking remainders

* Remove IS_V20_MODEL flag always being True

Co-authored-by: apolinario <joaopaulo.passos+multimodal@gmail.com>
 2022-12-13 12:44:20 +01:00
Suvaditya Mukherjee
40c16ed2f0 Added Community pipeline for comparing Stable Diffusion v1.1-4 checkpoints (#1584) 
* Added Community pipeline for comparing Stable Diffusion v1.1-4

Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* Made changes to provide support for current iteration of from_pretrained and added example

Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* updated a small spelling error

Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* added pipeline entry to table

Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>
 2022-12-13 11:31:30 +01:00
Patrick von Platen
69de9b2eaa [Textual Inversion] Do not update other embeddings (#1665) 2022-12-12 17:44:39 +01:00
Patrick von Platen
3ce6380d3a [SD] Make sure scheduler is correct when converting (#1667) 2022-12-12 16:57:48 +01:00
Cyberes
d2dc4de303 Handle missing global_step key in scripts/convert_original_stable_diffusion_to_diffusers.py (#1612) 
handle missing global_step key and don't download config if it already exists
 2022-12-12 16:10:52 +01:00
Kangfu Mei
ded3299d68 fix bug if we don't do_classifier_free_guidance (#1601) 
* fix bug if we don't do_classifier_free_guidance

* update for copied diffusers.pipelines..alt_diffusion..pipeline_alt_diffusion.AltDiffusionPipeline
 2022-12-12 15:02:13 +01:00
Patrick von Platen
8bf5e59931 Deprecate init image correctly (#1649) 
Deprecate init image correctl
 2022-12-12 15:00:20 +01:00
Prathik Rao
4645e28355 tensor format ort bug fix (#1557) 
bug fix

Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: anton- <anton@huggingface.co>
 2022-12-12 13:56:02 +01:00
Lukas Struppek
589330595d VersatileDiffusion: fix input processing (#1568) 
* fix versatile diffusion input

* merge main

* `make fix-copies`

Co-authored-by: anton- <anton@huggingface.co>
 2022-12-12 13:45:27 +01:00
lawfordp2017
31444f5790 Add text encoder conversion (#1559) 
* Initial code for attempt at improving SD <--> diffusers conversions for v2.0

* Updates to support round-trip between orig. SD 2.0 and diffusers models

* Corrected formatting to Black standard

* Correcting import formatting

* Fixed imports (properly this time)

* add some corrections

* remove inference files

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-12-12 10:07:42 +01:00
M-A
c3b2f97534 Remove unnecessary kwargs in depth2img (#1648) 
Since no deprecate() call was done, the typos were silently ignored.
 2022-12-11 17:00:50 +01:00
Patrick von Platen
fc94c60c83 Remove unnecessary offset in img2img (#1653) 
remove unnecessary offset in img2img
 2022-12-10 19:26:25 +01:00
Pedro Cuenca
ea64a7860a Allow k pipeline to generate > 1 images (#1645) 
Allow k pipeline to generate > 1 images.
 2022-12-10 17:54:02 +01:00
Tim Hinderliter
2868d99181 dreambooth: fix #1566: maintain fp32 wrapper when saving a checkpoint to avoid crash when running fp16 (#1618) 
* dreambooth: fix #1566: maintain fp32 wrapper when saving a checkpoint to avoid crash when running fp16

* dreambooth: guard against passing keep_fp32_wrapper arg to older versions of accelerate. part of fix for #1566

* Apply suggestions from code review

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

* Update examples/dreambooth/train_dreambooth.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-12-10 15:45:45 +01:00
Pedro Cuenca
0c18d02cc9 Remove spurious arg in training scripts (#1644) 
Remove spurious arg in training scripts.
 2022-12-10 13:57:20 +01:00
Patrick von Platen
6b68afd8e4 do not automatically enable xformers (#1640) 
* do not automatically enable xformers

* uP
 2022-12-09 18:28:36 +01:00
anton-
63c4944998 Patch release: v0.10.2 2022-12-09 17:59:32 +01:00
Anton Lozhkov
3ebe40fc5f Adapt to forced transformers version in some dependent libraries (#1638) 
* Adapt to forced transformers version in some dependent libraries

* style

* Update __init__.py

* update requires_backends
 2022-12-09 17:42:53 +01:00
Anton Lozhkov
089252542c V0.10.1 patch (#1637) 
* Re-add xformers enable to UNet2DCondition (#1627)

* finish

* fix

* Update tests/models/test_models_unet_2d.py

* style

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

* Release: v0.10.1

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-12-09 17:04:25 +01:00
Patrick von Platen
cd91fc06fe Re-add xformers enable to UNet2DCondition (#1627) 
* finish

* fix

* Update tests/models/test_models_unet_2d.py

* style

Co-authored-by: Anton Lozhkov <anton@huggingface.co>
 2022-12-09 14:05:38 +01:00
Pedro Cuenca
ff65c2d72b Don't assume 512x512 in k-diffusion pipeline (#1625) 
Don't assume 512x512 in k-diffusion pipeline.
 2022-12-09 11:50:29 +01:00
Haofan Wang
f1b726e46e Update requirements.txt (#1623) 
* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt
 2022-12-09 08:35:27 +01:00
SkyTNT
f242eba4fd Fix lpw stable diffusion pipeline compatibility (#1622) 2022-12-09 08:30:26 +01:00
anton-
3faf204c49 Release: v0.10.0 v0.10.0 2022-12-08 19:24:10 +01:00
Suraj Patil
5383188c7e StableDiffusionDepth2ImgPipeline (#1531) 
* begin depth pipeline

* add depth estimation model

* fix prepare_depth_mask

* add a comment about autocast

* copied from, quality, cleanup

* begin tests

* handle tensors

* norm image tensor

* fix batch size

* fix tests

* fix enable_sequential_cpu_offload

* fix save load

* fix test_save_load_float16

* fix test_save_load_optional_components

* fix test_float16_inference

* fix test_cpu_offload_forward_pass

* fix test_dict_tuple_outputs_equivalent

* up

* fix fast tests

* fix test_stable_diffusion_img2img_multiple_init_images

* fix few more fast tests

* don't use device map for DPT

* fix test_stable_diffusion_pipeline_with_sequential_cpu_offloading

* accept external depth maps

* prepare_depth_mask -> prepare_depth_map

* fix file name

* fix file name

* quality

* check transformers version

* fix test names

* use skipif

* fix import

* add docs

* skip tests on mps

* correct version

* uP

* Update docs/source/api/pipelines/stable_diffusion_2.mdx

* fix fix-copies

* fix fix-copies

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: anton- <anton@huggingface.co>
 2022-12-08 18:25:12 +01:00
Anton Lozhkov
dbe0719246 Fix PyCharm/VSCode static type checking for dummy objects (#1596) 
* Fix PyCharm/VSCode static type checking for dummy objects

* Re-add dummies

* Fix AudioDiffusion imports

* fix import

* fix import

* Update utils/check_dummies.py

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

* Update src/diffusers/utils/import_utils.py

* Update src/diffusers/__init__.py

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

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

* fix double import

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-12-08 14:02:11 +01:00
Anton Lozhkov
03566d8689 Delete hi 2022-12-08 13:07:25 +01:00
Suraj Patil
a934e5bc6c [Versatile Diffusion] add upcast_attention (#1605) 
add upcast_attention arg
 2022-12-08 13:03:32 +01:00
Patrick von Platen
a643c6300e [K Diffusion] Add k diffusion sampler natively (#1603) 
* uP

* uP
 2022-12-08 12:48:37 +01:00
Ben Sherman
326de41915 Trivial fix for undefined symbol in train_dreambooth.py (#1598) 
easy fix for undefined name in train_dreambooth.py

import_model_class_from_model_name_or_path loads a pretrained model
and refers to args.revision in a context where args is undefined. I modified
the function to take revision as an argument and modified the invocation
of the function to pass in the revision from args. Seems like this was caused
by a cut and paste.
 2022-12-07 21:39:48 +01:00
Anton Lozhkov
eb1abee693 [ONNX] Fix flaky tests (#1593) 
* [ONNX] Fix flaky tests

* revert
 2022-12-07 19:53:13 +01:00
Pedro Cuenca
5e0369219f Make cross-attention check more robust (#1560) 
* Make cross-attention check more robust.

* Fix copies.
 2022-12-07 18:33:29 +01:00
Nathan Lambert
bea7eb4314 Update RL docs for better sharing / adding models (#1563) 
* init docs update

* style

* fix bad colab formatting, add pipeline comment

* update todo
 2022-12-07 09:08:12 -08:00