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
4,210 Commits 740 Branches 94 Tags
v0.29.2
Commit Graph

4210 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
sayakpaul
c586aadef6 Release: v0.29.2 v0.29.2 2024-06-27 09:19:56 +05:30
Sayak Paul
1479729dde [LoRA] fix vanilla fine-tuned lora loading. (#8691) 
fix vanilla fine-tuned lora loading.
 2024-06-27 09:17:44 +05:30
Sayak Paul
64b20500dc [Chore] remove deprecation from transformer2d regarding the output class. (#8698) 
* remove deprecation from transformer2d regarding the output class.

* up

* deprecate more
 2024-06-27 09:17:32 +05:30
Sayak Paul
aa2b3a3bb6 [LoRA] fix conversion utility so that lora dora loads correctly (#8688) 
fix conversion utility so that lora dora loads correctly
 2024-06-27 09:17:11 +05:30
Sayak Paul
edc1c8928b [LoRA] refactor lora conversion utility. (#8295) 
* refactor lora conversion utility.

* remove error raises.

* add onetrainer support too.
 2024-06-27 09:16:37 +05:30
Nan
a0a5427028 [SD3] Fix mis-matched shape when num_images_per_prompt > 1 using without T5 (text_encoder_3=None) (#8558) 
* fix shape mismatch when num_images_per_prompt > 1 and text_encoder_3=None

* style

* fix copies

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
v0.29.1 		2024-06-20 11:10:11 -10:00
YiYi Xu
dc74c7ec4f fix from_single_file for checkpoints with t5 (#8631) 
fix single file
 2024-06-20 11:06:47 -10:00
ηŽ‹ε₯‡ε‹‹
2eafde786a Support SD3 ControlNet and Multi-ControlNet. (#8566) 
* sd3 controlnet



---------

Co-authored-by: haofanwang <haofanwang.ai@gmail.com>
 2024-06-20 11:06:31 -10:00
Carolinabanana
7ec060d449 Fix gradient checkpointing issue for Stable Diffusion 3 (#8542) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-06-20 11:06:18 -10:00
Álvaro Somoza
828e364fbe [SD3 Inference] T5 Token limit (#8506) 
* max_sequence_length for the T5

* updated img2img

* apply suggestions

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-06-20 11:05:50 -10:00
Marc Sun
6ea08a90b0 Fix sharding when no device_map is passed (#8531) 
* Fix sharding when no device_map is passed

* style

* add tests

* align

* add docstring

* format

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-20 11:05:27 -10:00
Dhruv Nair
10ada4dae6 [Single File Loading] Handle unexpected keys in CLIP models when accelerate isn't installed. (#8462) 
* update

* update

* update

* update

* update

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-20 11:05:12 -10:00
Dhruv Nair
7fada49e29 Expand Single File support in SD3 Pipeline (#8517) 
* update

* update
 2024-06-20 11:04:02 -10:00
Beinsezii
46418bd752 Add Hunyuan AutoPipe mapping (#8505) 2024-06-20 11:03:44 -10:00
Beinsezii
80460d98e1 Add SD3 AutoPipeline mappings (#8489) 2024-06-20 11:03:19 -10:00
Sayak Paul
93b4b105a3 fix warning log for Transformer SD3 (#8496) 
fix warning log
 2024-06-20 11:02:39 -10:00
YiYi Xu
21ccde8209 prepare for patch release 2024-06-20 11:00:42 -10:00
sayakpaul
39aa3909e8 Release: v0.29.0 v0.29.0 2024-06-12 21:12:08 +01:00
Sayak Paul
ec068f9b5b fix dual transformer2d import (#8491) 
fix
 2024-06-12 21:10:27 +01:00
Ameer Azam
0240d4191a Update README_sd3.md (#8490) 
becasue in  Readme  it was not correct
train_dreambooth_sd3.py to train_dreambooth_lora_sd3
 2024-06-12 21:08:36 +01:00
Dhruv Nair
04717fd861 Add Stable Diffusion 3 (#8483) 
* up

* add sd3

* update

* update

* add tests

* fix copies

* fix docs

* update

* add dreambooth lora

* add LoRA

* update

* update

* update

* update

* import fix

* update

* Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* import fix 2

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* update

* update

* update

* fix ckpt id

* fix more ids

* update

* missing doc

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

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

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

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

* update'

* fix

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* note on gated access.

* requirements

* licensing

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-06-12 20:44:00 +01:00
Jiwook Han
6fd458e99d 🌐 [i18n-KO] Translated conceptual/philosophy.md and 3 other documents to Korean (#8294) 
* translation about 3 documents into Korean

* evaluation doc korean translation

* _toctree.yml modify

* doc title fix : philosopy->philosophy

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/ethical_guidelines.md

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update docs/source/ko/conceptual/evaluation.md

Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>

* Update philosophy.md (from jungnerd)

---------

Co-authored-by: Jihun Lim <31366038+heuristicwave@users.noreply.github.com>
Co-authored-by: Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr>
 2024-06-12 09:40:37 -07:00
Greg Hunkins
1066fe4cbc 🀫 Quiet IP Adapter Mask Warning (#8475) 
* quiet attn parameters

* fix lint

* make style && make quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-12 16:50:13 +01:00
Sayak Paul
d38f69ea25 change max_shard_size to 10GB (#8445) 
* change max_shard_size to 10GB

* add notes to the documentation

* Update src/diffusers/models/modeling_utils.py

Co-authored-by: Lucain <lucainp@gmail.com>

* change to abs limit

---------

Co-authored-by: Lucain <lucainp@gmail.com>
 2024-06-12 13:49:13 +01:00
Patrick
0a1c13af79 image_processor.py: Fixed an error in ValueError's message (#8447) 
* image_processor.py: Fixed an error in ValueError's message , as the string's join method tried to join types, instead of strings

Bug that occurred:

f"Input is in incorrect format. Currently, we only support {', '.join(supported_formats)}"
TypeError: sequence item 0: expected str instance, type found

* Fixed: C417 Unnecessary `map` usage (rewrite using a generator expression)

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-11 08:09:24 -10:00
YiYi Xu
0028c34432 fix SEGA pipeline (#8467) 
* fix

* style

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-11 06:37:49 -10:00
Sayak Paul
d457beed92 Update README.md to update the MaPO project (#8470) 
Update README.md
 2024-06-11 10:10:45 +01:00
Jianqi Pan
1d9a6a81b9 πŸ”§ chore: use modeling_outputs.Transformer2DModelOutput (#8436) 
* πŸ”§ chore: use modeling_outputs.Transformer2DModelOutput

* πŸ”§ chore: isort

* πŸ”§ chore: isort

* style

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
 2024-06-10 12:11:41 +01:00
Luc Georges
4e0984db6c fix(ci): remove unnecessary permissions (#8457) 2024-06-10 10:49:29 +01:00
Luc Georges
83bc6c94ea feat(ci): add trufflehog secrets detection (#8430) 2024-06-08 07:56:47 +05:30
Lucain
0d68ddf327 Move away from cached_download (#8419) 
* Move away from

* unused constant

* Add custom error
 2024-06-07 15:43:00 +05:30
Sayak Paul
7d887118b9 [Core] support saving and loading of sharded checkpoints (#7830) 
* feat: support saving a model in sharded checkpoints.

* feat: make loading of sharded checkpoints work.

* add tests

* cleanse the loading logic a bit more.

* more resilience while loading from the Hub.

* parallelize shard downloads by using snapshot_download()/

* default to a shard size.

* more fix

* Empty-Commit

* debug

* fix

* uality

* more debugging

* fix more

* initial comments from Benjamin

* move certain methods to loading_utils

* add test to check if the correct number of shards are present.

* add a test to check if loading of sharded checkpoints from the Hub is okay

* clarify the unit when passed as an int.

* use hf_hub for sharding.

* remove unnecessary code

* remove unnecessary function

* lucain's comments.

* fixes

* address high-level comments.

* fix test

* subfolder shenanigans./

* Update src/diffusers/utils/hub_utils.py

Co-authored-by: Lucain <lucainp@gmail.com>

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

* remove _huggingface_hub_version as not needed.

* address more feedback.

* add a test for local_files_only=True/

* need hf hub to be at least 0.23.2

* style

* final comment.

* clean up subfolder.

* deal with suffixes in code.

* _add_variant default.

* use weights_name_pattern

* remove add_suffix_keyword

* clean up downloading of sharded ckpts.

* don't return something special when using index.json

* fix more

* don't use bare except

* remove comments and catch the errors better

* fix a couple of things when using is_file()

* empty

---------

Co-authored-by: Lucain <lucainp@gmail.com>
 2024-06-07 14:49:10 +05:30
Lucain
b63c956860 Final fix for mirror community pipeline (#8427) 2024-06-07 11:08:33 +02:00
Lucain
716b2062bf Fix mirror community pipeline (#8426) 2024-06-07 11:03:48 +02:00
Lucain
5fd6825d25 Fix mirror_community_pipeline.yml name (#8425) 2024-06-07 11:00:05 +02:00
Lucain
e0fae6fd73 Mirror ./examples/community folder on HF (#8417) 
* first draft

* secret

* tiktok

* capital matters

* dataset matter

* don't be a prick

* refact

* only on main or tag

* document with an example

* Update destination dataset

* link

* allow manual trigger

* better

* lin

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-07 10:56:05 +02:00
Tolga CangΓΆz
ec1aded12e Optimize test files by fixing CPU-offloading usage (#8409) 
* Refactor code to remove unnecessary calls to `to(torch_device)`

* Refactor code to remove unnecessary calls to `to("cuda")`

* Update pipeline_stable_diffusion_diffedit.py
 2024-06-06 09:51:26 -10:00
Steven Liu
151a56b80e [docs] Single file usage (#8412) 
* single file usage

* edit
 2024-06-06 12:40:34 -07:00
Sayak Paul
a3faf3f260 [Core] fix: legacy model mapping (#8416) 
* fix: legacy model mapping

* remove print
 2024-06-06 20:35:05 +05:30
Sayak Paul
867a2b0cf9 [Hunyuan] add optimization related sections to the hunyuan dit docs. (#8402) 
* optimizations to the hunyuan dit docs.

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/pipelines/hunyuandit.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-06-06 05:41:38 +05:30
Tolga CangΓΆz
98730c5dd7 Errata (#8322) 
* Fix typos

* Trim trailing whitespaces

* Remove a trailing whitespace

* chore: Update MarigoldDepthPipeline checkpoint to prs-eth/marigold-lcm-v1-0

* Revert "chore: Update MarigoldDepthPipeline checkpoint to prs-eth/marigold-lcm-v1-0"

This reverts commit fd742b30b4.

* pokemon -> naruto

* `DPMSolverMultistep` -> `DPMSolverMultistepScheduler`

* Improve Markdown stylization

* Improve style

* Improve style

* Refactor pipeline variable names for consistency

* up style
 2024-06-05 13:59:09 -07:00
Guillaume LEGENDRE
7ebd359446 Update tailscale action to main (#8403) 2024-06-05 18:53:33 +05:30
Hzzone
d3881f35b7 Gligen training (#7906) 
* add training code of gligen

* fix code quality tests.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-05 16:26:42 +04:00
Sayak Paul
48207d6689 [Scheduler] fix: EDM schedulers when using the exp sigma schedule. (#8385) 
* fix: euledm when using the exp sigma schedule.

* fix-copies

* remove print.

* reduce friction

* yiyi's suggestioms
 2024-06-04 19:31:43 -10:00
Sayak Paul
2f6f426f66 [Hunyuan] allow Hunyuan DiT to run under 6GB for GPU VRAM (#8399) 
* allow hunyuan dit to run under 6GB for GPU VRAM

* add section in the docs/
 2024-06-05 08:24:19 +04:00
Sayak Paul
a0542c1917 [LoRA] Remove legacy LoRA code and related adjustments (#8316) 
* remove legacy code from load_attn_procs.

* finish first draft

* fix more.

* fix more

* add test

* add serialization support.

* fix-copies

* require peft backend for lora tests

* style

* fix test

* fix loading.

* empty

* address benjamin's feedback.
 2024-06-05 08:15:30 +04:00
Sayak Paul
a8ad6664c2 [Hunyuan] feat: support chunked ff. (#8397) 
feat: support chunked ff.
 2024-06-05 08:12:18 +04:00
Sayak Paul
14f7b545bd [Hunyuan DiT] feat: enable fusing qkv projections when doing attention (#8396) 
* feat: introduce qkv fusion for Hunyuan

* fix copies
 2024-06-05 07:58:03 +04:00
leaps
07cd20041c Update code example in pipeline_stable_unclip_img2img.py EXAMPLE_DOC_STRING (#8401) 
Update code example in pipeline_stable_unclip_img2img.py

Previous code caused an error when run
 2024-06-04 17:22:46 -10:00
Sayak Paul
6ddbf6222c [Transformer2DModel] Handle norm_type safely while remapping (#8370) 
* handle norm_type of transformer2d_model safely.

* log an info when old model class is being returned.

* Apply suggestions from code review

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* remove extra stuff

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-06-04 13:39:19 +04:00