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
2,258 Commits 740 Branches 94 Tags
a80f6966cfb2fdfc60ce5fcc7666ebf671ae620f
Commit Graph

2258 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Will Berman
a80f6966cf [docs] add notes for stateful model changes (#3252) 
* [docs] add notes for stateful model changes

* Update docs/source/en/optimization/fp16.mdx

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

* link to accelerate docs for discarding hooks

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-05-05 07:23:51 -07:00
YiYi Xu
2c87f6571c update notebook (#3259) 
Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>
 2023-05-05 07:23:51 -07:00
Patrick von Platen
12868b125a Fix community pipelines (#3266) 2023-05-05 07:23:51 -07:00
Patrick von Platen
79706a7db8 Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline"" (#3265) 
Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline" (#3201)"

This reverts commit 91a2a80eb2.
 2023-05-05 07:23:51 -07:00
Robert Dargavel Smith
9585b2308d AudioDiffusionPipeline - fix encode method after config changes (#3114) 
* config fixes

* deprecate get_input_dims
 2023-05-05 07:23:51 -07:00
Jair Trejo
5f3b10afb5 Fix typo in textual inversion JAX training script (#3123) 
The pipeline is built as `pipe` but then used as `pipeline`.
 2023-05-05 07:23:50 -07:00
Xie Zejian
cd13b10431 fix typo in score sde pipeline (#3132) 2023-05-05 07:23:50 -07:00
apolinário
1147c76eca Update IF name to XL (#3262) 
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com>
 2023-05-05 07:23:50 -07:00
Ernie Chu
76e5941cb2 [docs] Update interface in repaint.mdx (#3119) 
Update repaint.mdx

accomodate to #1701
 2023-05-05 07:23:50 -07:00
Isaac
cf2bf70a4d adding required parameters while calling the get_up_block and get_down_block (#3210) 
* removed unnecessary parameters from get_up_block and get_down_block functions

* adding resnet_skip_time_act, resnet_out_scale_factor and cross_attention_norm to get_up_block and get_down_block functions

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-05-05 07:23:50 -07:00
Pedro Cuenca
97cf3866db Remove required from tracker_project_name (#3260) 
Remove required from tracker_project_name.

As observed by https://github.com/off99555 in https://github.com/huggingface/diffusers/issues/2695#issuecomment-1470755050, it already has a default value.
 2023-05-05 07:23:50 -07:00
Nipun Jindal
8def721ec8 [Stochastic Sampler][Slow Test]: Cuda test fixes (#3257) 
[Slow Test]: Cuda test fixes

Co-authored-by: njindal <njindal@adobe.com>
 2023-05-05 07:23:50 -07:00
Nipun Jindal
7880ed77fb [2064]: Add stochastic sampler (sample_dpmpp_sde) (#3020) 
* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* Review comments

* [Review comment]: Add is_torchsde_available()

* [Review comment]: Test and docs

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

---------

Co-authored-by: njindal <njindal@adobe.com>
 2023-05-05 07:23:50 -07:00
Pedro Cuenca
a640f1ba96 Write model card in controlnet training script (#3229) 
Write model card in controlnet training script.
 2023-05-05 07:23:50 -07:00
Pedro Cuenca
59986b6c56 [docs] only mention one stage (#3246) 
* [docs] only mention one stage

* add blurb on auto accepting

---------

Co-authored-by: William Berman <WLBberman@gmail.com>
 2023-05-05 07:23:50 -07:00
Patrick von Platen
163c33b5ff Post release for 0.16.0 (#3244) 
* Post release

* fix more
 2023-05-05 07:23:50 -07:00
Patrick von Platen
4cc60b53d8 Release: v0.16.0 2023-05-05 07:23:50 -07:00
Sanchit Gandhi
f83fbbdc56 [AudioLDM] Update docs to use updated ckpt (#3240) 
* [AudioLDM] Update docs to use updated ckpt

* make style
 2023-05-05 07:23:50 -07:00
Sayak Paul
81d7eba83f Adds a document on token merging (#3208) 
* add document on token merging.

* fix headline.

* fix: headline.

* add some samples for comparison.
 2023-05-05 07:23:50 -07:00
Patrick von Platen
4c73947fd3 fix fast test (#3241) 2023-05-05 07:23:50 -07:00
Patrick von Platen
3acc87952b Allow fp16 attn for x4 upscaler (#3239) 
* Add all files

* update

* Make sure vae is memory efficient for PT 1

* make style
 2023-05-05 07:23:50 -07:00
Patrick von Platen
7ad77dde16 Allow return pt x4 (#3236) 
* Add all files

* update
 2023-05-05 07:23:50 -07:00
Patrick von Platen
416f31adf8 add model (#3230) 
* add

* clean

* up

* clean up more

* fix more tests

* Improve docs further

* improve

* more fixes docs

* Improve docs more

* Update src/diffusers/models/unet_2d_condition.py

* fix

* up

* update doc links

* make fix-copies

* add safety checker and watermarker to stage 3 doc page code snippets

* speed optimizations docs

* memory optimization docs

* make style

* add watermarking snippets to doc string examples

* make style

* use pt_to_pil helper functions in doc strings

* skip mps tests

* Improve safety

* make style

* new logic

* fix

* fix bad onnx design

* make new stable diffusion upscale pipeline model arguments optional

* define has_nsfw_concept when non-pil output type

* lowercase linked to notebook name

---------

Co-authored-by: William Berman <WLBberman@gmail.com>
 2023-05-05 07:23:50 -07:00
Patrick von Platen
711119ae7a Fix docs text inversion (#3166) 
* Fix docs text inversion

* Apply suggestions from code review
 2023-05-05 07:22:14 -07:00
Yuchen Fan
81950af961 Sync cache version check from transformers (#3179) 
sync cache version check from transformers
 2023-05-05 07:22:14 -07:00
pdoane
9e2f445125 Fix issue in maybe_convert_prompt (#3188) 
When the token used for textual inversion does not have any special symbols (e.g. it is not surrounded by <>), the tokenizer does not properly split the replacement tokens.  Adding a space for the padding tokens fixes this.
 2023-05-05 07:22:14 -07:00
Patrick von Platen
0431637f11 Add ControlNet v1.1 docs (#3226) 
Add v1.1 docs
 2023-05-05 07:22:14 -07:00
Isaac
167cb7ae17 adding enable_vae_tiling and disable_vae_tiling functions (#3225) 
adding enable_vae_tiling and disable_val_tiling functions
 2023-05-05 07:22:14 -07:00
Lucca Zenóbio
4e03663091 fix mixed precision training on train_dreambooth_inpaint_lora (#3138) 
cast to weight dtype
 2023-05-05 07:22:14 -07:00
Patrick von Platen
895320910c [Bug fix] Fix batch size attention head size mismatch (#3214) 2023-05-05 07:22:14 -07:00
Will Berman
de05ea0f50 Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline" (#3201) 
Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline (#3197)"

This reverts commit 9965cb50ea.
 2023-05-05 07:22:14 -07:00
Patrick von Platen
3267649480 Make sure VAE attention works with Torch 2_0 (#3200) 
* Make sure attention works with Torch 2_0

* make style

* Fix more
 2023-05-05 07:22:14 -07:00
SkyTNT
a69502f844 [Community Pipelines] Update lpw_stable_diffusion pipeline (#3197) 
* Update lpw_stable_diffusion.py

* fix cpu offload
 2023-05-05 07:22:14 -07:00
Chengrui Wang
49c9b4ce5f Fix bug in train_dreambooth_lora (#3183) 
* Update train_dreambooth_lora.py

fix bug

* Update train_dreambooth_lora.py
 2023-05-05 07:22:14 -07:00
Sanchit Gandhi
43c90b0873 [AudioLDM] Fix dtype of returned waveform (#3189) 2023-05-05 07:22:14 -07:00
Youssef Adarrab
c729403042 Add Karras sigmas to HeunDiscreteScheduler (#3160) 
* Add karras pattern to discrete heun scheduler

* Add integration test

* Fix failing CI on pytorch test on M1 (mps)

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-05-05 07:22:14 -07:00
Patrick von Platen
cf3576364a Multi Vector Textual Inversion (#3144) 
* Multi Vector

* Improve

* fix multi token

* improve test

* make style

* Update examples/test_examples.py

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* update

* Finish

* Apply suggestions from code review

---------

Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2023-05-05 07:22:14 -07:00
Steven Liu
15a90e2741 [docs] Clarify training args (#3146) 
* clarify training arg

* apply feedback
 2023-05-05 07:22:14 -07:00
YiYi Xu
c98a05510a make from_flax work for controlnet (#3161) 
fix from_flax

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-05-05 07:22:14 -07:00
asfiyab-nvidia
dac4d4a5c2 Fix TensorRT community pipeline device set function (#3157) 
pass silence_dtype_warnings as kwarg

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-05-05 07:22:14 -07:00
Sayak Paul
006ae03a90 Update custom_diffusion.mdx to credit the author (#3163) 
* Update custom_diffusion.mdx

* fix: unnecessary list comprehension.
 2023-05-05 07:22:14 -07:00
Steven Liu
e21784e173 [docs] Deterministic algorithms (#3172) 
deterministic algos
 2023-05-05 07:22:14 -07:00
Patrick von Platen
4366b0c7e7 Add model offload to x4 upscaler (#3187) 
* Add model offload to x4 upscaler

* fix
 2023-05-05 07:22:14 -07:00
regisss
6ad4392443 Update Habana Gaudi documentation (#3169) 
* Update Habana Gaudi doc

* Fix tables
 2023-05-05 07:22:14 -07:00
Sayak Paul
206b9b69d1 [DreamBooth] add text encoder LoRA support in the DreamBooth training script (#3130) 
* add: LoRA text encoder support for DreamBooth example.

* fix initialization.

* fix: modification call.

* add: entry in the readme.

* use dog dataset from hub.

* fix: params to clip.

* add entry to the LoRA doc.

* add: tests for lora.

* remove unnecessary list comprehension./
 2023-05-05 07:22:14 -07:00
clarencechen
f99a9ffab9 Update Noise Autocorrelation Loss Function for Pix2PixZero Pipeline (#2942) 
* Update Pix2PixZero Auto-correlation Loss

* Add fast inversion tests

* Clarify purpose and mark as deprecated

Fix inversion prompt broadcasting

* Register modules set to `None` in config for `test_save_load_optional_components`

* Update new tests to coordinate with #2953
 2023-05-05 07:22:14 -07:00
XinyuYe-Intel
abd21daa45 Added distillation for quantization example on textual inversion. (#2760) 
* Added distillation for quantization example on textual inversion.

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* refined readme and code style.

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* Update text2images.py

* refined code of model load and added compatibility check.

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* fixed code style.

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* fix C403 [*] Unnecessary `list` comprehension (rewrite as a `set` comprehension)

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

---------

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>
 2023-05-05 07:22:14 -07:00
Mishig
3306b04b43 Update custom_diffusion.mdx (#3165) 
Add missing newlines for rendering the links correctly
 2023-05-05 07:22:14 -07:00
Patrick von Platen
4a6aee9828 make style 2023-05-05 07:22:14 -07:00
nupurkmr9
3417b1f51c adding custom diffusion training to diffusers examples (#3031) 
* diffusers==0.14.0 update

* custom diffusion update

* custom diffusion update

* custom diffusion update

* custom diffusion update

* custom diffusion update

* custom diffusion update

* custom diffusion

* custom diffusion

* custom diffusion

* custom diffusion

* custom diffusion

* apply formatting and get rid of bare except.

* refactor readme and other minor changes.

* misc refactor.

* fix: repo_id issue and loaders logging bug.

* fix: save_model_card.

* fix: save_model_card.

* fix: save_model_card.

* add: doc entry.

* refactor doc,.

* custom diffusion

* custom diffusion

* custom diffusion

* apply style.

* remove tralining whitespace.

* fix: toctree entry.

* remove unnecessary print.

* custom diffusion

* custom diffusion

* custom diffusion test

* custom diffusion xformer update

* custom diffusion xformer update

* custom diffusion xformer update

---------

Co-authored-by: Nupur Kumari <nupurkumari@Nupurs-MacBook-Pro.local>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nupur Kumari <nupurkumari@nupurs-mbp.wifi.local.cmu.edu>
 2023-05-05 07:22:14 -07:00