AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
1,958 Commits 742 Branches 94 Tags
ebd44957fc2e162b584fddb0b9e7bf5156419fed
Commit Graph

1958 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Will Berman
ebd44957fc image generation main process checks (#2631) 2023-03-14 01:28:03 -07:00
Haiwen Huang
e2d9a9bea0 fix the in-place modification in unet condition when using controlnet (#2586) 
* fix the in-place modification in unet condition when using controlnet, which will cause backprop errors when training

* add clone to mid block

* fix-copies

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: William Berman <WLBberman@gmail.com>
 2023-03-14 01:23:03 -07:00
Sayak Paul
f9cfb5ab8a [Tests] Adds a test suite for EMAModel (#2530) 
* ema test cases.

* debugging maessages.

* debugging maessages.

* add: tests for ema.

* fix: optimization_step arg,

* handle device placement.

* Apply suggestions from code review

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

* remove del and gc.

* address PR feedback.

* add: tests for serialization.

* fix: typos.

* skip_mps to serialization.

---------

Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-14 10:54:45 +05:30
Takuma Mori
d9b8adc4ca Add support for Multi-ControlNet to StableDiffusionControlNetPipeline (#2627) 
* support for List[ControlNetModel] on init()

* Add to support for multiple ControlNetCondition

* rename conditioning_scale to scale

* scaling bugfix

* Manually merge `MultiControlNet` #2621

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

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

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

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

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

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

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

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

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

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

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

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

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

* cleanups
- don't expose ControlNetCondition
- move scaling to ControlNetModel

* make style error correct

* remove ControlNetCondition to reduce code diff

* refactoring image/cond_scale

* add explain for `images`

* Add docstrings

* all fast-test passed

* Add a slow test

* nit

* Apply suggestions from code review

* small precision fix

* nits

MultiControlNet -> MultiControlNetModel - Matches existing naming a bit
closer

MultiControlNetModel inherit from model utils class - Don't have to
re-write fp16 test

Skip tests that save multi controlnet pipeline - Clearer than changing
test body

Don't auto-batch the number of input images to the number of controlnets.
We generally like to require the user to pass the expected number of
inputs. This simplifies the processing code a bit more

Use existing image pre-processing code a bit more. We can rely on the
existing image pre-processing code and keep the inference loop a bit
simpler.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: William Berman <WLBberman@gmail.com>
 2023-03-13 21:18:30 +01:00
Patrick von Platen
4ae54b3789 [attention] Fix attention (#2656) 
* [attention] Fix attention

* fix

* correct
 2023-03-13 19:10:33 +01:00
M. Tolga Cangöz
fa7a576191 Update schedulers.mdx (#2647) 
Fix typos
 2023-03-13 16:41:28 +01:00
Aki Sakurai
6766a811ff Support non square image generation for StableDiffusionSAGPipeline (#2629) 
* Support non square image generation for StableDiffusionSAGPipeline

* Fix style
 2023-03-13 11:49:06 +01:00
M. Tolga Cangöz
bbab855322 Update loading.mdx (#2642) 
Fix typos
 2023-03-11 16:49:05 +01:00
Steven Liu
d5ce55293c [docs] Build Jax notebooks for real (#2641) 
build jax notebooks for real
 2023-03-11 01:21:14 +01:00
Patrick von Platen
1a7e9f13fd [Pipeline loading] Remove send_telemetry (#2640) 
* [Pipeline loading]

* up
 2023-03-10 21:01:59 +01:00
Steven Liu
c460ef61b3 [docs] Update readme (#2612) 
* 📝 update readme

* 🖍 apply feedback
 2023-03-10 08:32:43 -08:00
Will Berman
a28acb5dcc controlnet sd 2.1 checkpoint conversions (#2593) 
* controlnet sd 2.1 checkpoint conversions

* remove global_step -> make config file mandatory
 2023-03-10 08:22:02 -08:00
M. Tolga Cangöz
f1ab955f64 Update basic_training.mdx (#2639) 
Add 'import os'
 2023-03-10 14:19:12 +01:00
M. Tolga Cangöz
9360bb94c3 Update quicktour.mdx (#2637) 
Fix typo
 2023-03-10 14:17:10 +01:00
Ruizhe Wang
ce08cb72fb [Dreambooth] Editable number of class images (#2251) 
* [Dreambooth] Editable number of class images

* 'class_num=None' bug fix

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-10 14:15:16 +01:00
Sian
4aa68291a9 add translated docs (#2587) 
* add translated docs

* improve translated content

* improve translated content

* Modify the translation content
 2023-03-10 13:55:12 +01:00
Patrick von Platen
d761b58bfc [From pretrained] Speed-up loading from cache (#2515) 
* [From pretrained] Speed-up loading from cache

* up

* Fix more

* fix one more bug

* make style

* bigger refactor

* factor out function

* Improve more

* better

* deprecate return cache folder

* clean up

* improve tests

* up

* upload

* add nice tests

* simplify

* finish

* correct

* fix version

* rename

* Apply suggestions from code review

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

* rename

* correct doc string

* correct more

* Apply suggestions from code review

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

* apply code suggestions

* finish

---------

Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-03-10 11:56:10 +01:00
Will Berman
7fe638c502 update paint by example docs (#2598) 2023-03-09 15:57:07 -08:00
Peter Lin
c812d97d5b Improve ddim scheduler and fix bug when prediction type is "sample" (#2094) 
Improve ddim scheduler

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-09 20:32:30 +01:00
Patrick von Platen
c5f6c538fd [Tests] Split scheduler tests (#2630) 
* up

* correct some

* up

* finish
 2023-03-09 19:11:47 +01:00
Patrick von Platen
6a7a5467ca Up vesion at which we deprecate "revision='fp16'" since transformers is not released yet (#2623) 
* improve error message

* upload
 2023-03-09 16:13:55 +01:00
Patrick von Platen
0650d641a3 Revert "[docs] Build notebooks from Markdown" (#2625) 
Revert "[docs] Build notebooks from Markdown (#2570)"

This reverts commit 78507bda24.
 2023-03-09 15:45:24 +01:00
Patrick von Platen
5d550cfd9e Make sure that DEIS, DPM and UniPC can correctly be switched in & out (#2595) 
* [Schedulers] Correct config changing

* uP

* add tests
 2023-03-09 14:17:19 +01:00
Patrick von Platen
24d624a486 Add cache_dir to docs (#2624) 
Improve docs
 2023-03-09 14:00:36 +01:00
Steven Liu
251a34add8 Migrate blog content to docs (#2477) 
* first draft

* ✨ minor edits

* 💄 make style

* oops add to toc

* 🖍 reframe around understanding components

* 🖍 apply feedback

* 🖍 apply feedback
 2023-03-09 13:20:49 +01:00
M. Tolga Cangöz
ded3174238 Fix typos (#2608) 2023-03-09 13:19:18 +01:00
Patrick von Platen
ef504c7880 make style 2023-03-09 13:01:00 +01:00
YiYi Xu
a062e47ec3 add flax pipelines to api doc + doc string examples (#2600) 
* add api doc for flax pipeline + doc string examples

* make style

---------

Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-09 13:00:29 +01:00
Antoine Bouthors
75f1210a0c Fixed incorrect width/height assignment in StableDiffusionDepth2ImgPi… (#2558) 
Fixed incorrect width/height assignment in StableDiffusionDepth2ImgPipeline when passing in tensor
 2023-03-09 10:55:36 +01:00
Víctor Martínez
186689affd fix: un-existing tmp config file in linux, avoid unnecessary disk IO (#2591) 2023-03-08 20:20:09 +01:00
Patrick von Platen
cbbad0af69 correct example 2023-03-08 20:14:19 +01:00
Haofan Wang
00132de359 Support LoRA for text encoder (#2588) 
* add lora

* Update examples/research_projects/lora/README.md

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-08 20:14:01 +01:00
Ella Charlaix
a5d2ee9d47 Add OpenVINO documentation (#2569) 
* Add OpenVINO documentation

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

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

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2023-03-08 20:07:44 +01:00
Steven Liu
68545a15d9 [docs] Update unconditional image generation docs (#2592) 
* 📝 update and minor refactor

* ✨ minor edits
 2023-03-08 09:47:49 -08:00
Patrick von Platen
445a176bde [Docs] Fix link to colab (#2604) 2023-03-08 12:59:58 +01:00
Steven Liu
78507bda24 [docs] Build notebooks from Markdown (#2570) 
* 📝 add mechanism for building colab notebook

* 🖍 add notebooks to correct folder

* 🖍 fix folder name
 2023-03-08 12:13:19 +01:00
YiYi Xu
d2a5247a1f Add notebook doc img2img (#2472) 
* convert img2img.mdx into notebook doc

* fix

* Update docs/source/en/using-diffusers/img2img.mdx

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

---------

Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-07 20:00:56 -10:00
Will Berman
309d8cf9ab add deps table check updated to ci (#2590) 2023-03-07 15:24:44 -08:00
Steven Liu
b285d94e10 [docs] Move Textual Inversion training examples to docs (#2576) 
* 📝 add textual inversion examples to docs

* 🖍 apply feedback

* 🖍 add colab link
 2023-03-07 14:21:18 -08:00
clarencechen
55660cfb6d Improve dynamic thresholding and extend to DDPM and DDIM Schedulers (#2528) 
* Improve dynamic threshold

* Update code

* Add dynamic threshold to ddim and ddpm

* Encapsulate and leverage code copy mechanism

Update style

* Clean up DDPM/DDIM constructor arguments

* add test

* also add to unipc

---------

Co-authored-by: Peter Lin <peterlin9863@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-07 23:10:26 +01:00
Michael Gartsbein
46bef6e31d community stablediffusion controlnet img2img pipeline (#2584) 
Co-authored-by: mishka <gartsocial@gmail.com>
 2023-03-07 13:31:56 -08:00
Patrick von Platen
22a31760c4 [Docs] Weight prompting using compel (#2574) 
* add docs

* correct

* finish

* Apply suggestions from code review

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

* update deps table

* Apply suggestions from code review

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

---------

Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-03-07 20:26:33 +01:00
zxypro
f0b661b8fb [Docs]Fix invalid link to Pokemons dataset (#2583) 2023-03-07 14:26:09 +01:00
Isamu Isozaki
8552fd7efa Added multitoken training for textual inversion. Issue 369 (#661) 
* Added multitoken training for textual inversion

* Updated assertion

* Removed duplicate save code

* Fixed undefined bug

* Fixed save

* Added multitoken clip model +util helper

* Removed code splitting

* Removed class

* Fixed errors

* Fixed errors

* Added loading functionality

* Loading via dict instead

* Fixed bug of invalid index being loaded

* Fixed adding placeholder token only adding 1 token

* Fixed bug when initializing tokens

* Fixed bug when initializing tokens

* Removed flawed logic

* Fixed vector shuffle

* Fixed tokenizer's inconsistent __call__ method

* Fixed tokenizer's inconsistent __call__ method

* Handling list input

* Added exception for adding invalid tokens to token map

* Removed unnecessary files and started working on progressive tokens

* Set at minimum load one token

* Changed to global step

* Added method to load automatic1111 tokens

* Fixed bug in load

* Quality+style fixes

* Update quality/style fixes

* Cast embeddings to fp16 when loading

* Fixed quality

* Started moving things over

* Clearing diffs

* Clearing diffs

* Moved everything

* Requested changes
 2023-03-07 12:09:36 +01:00
Hu Ye
e09a7d01c8 fix the default value of doc (#2539) 2023-03-07 11:40:22 +01:00
Pedro Cuenca
d3ce6f4b1e Support revision in Flax text-to-image training (#2567) 
Support revision in Flax text-to-image training.
 2023-03-07 08:16:31 +01:00
Steven Liu
ff91f154ee Update quicktour (#2463) 
* first draft of updated quicktour

* 🖍 apply feedbacks

* 🖍 apply feedback and minor edits

* 🖍 add link to safety checker
 2023-03-06 13:45:36 -08:00
Steven Liu
62bea2df36 [docs] Move text-to-image LoRA training from blog to docs (#2527) 
* include text2image lora training in docs

* 🖍 apply feedback

* 🖍 minor edits
 2023-03-06 13:45:07 -08:00
Steven Liu
9136be14a7 [docs] Move DreamBooth training materials to docs (#2547) 
* move dbooth github stuff to docs

* add notebooks

* 🖍 minor shuffle

* 🖍 fix markdown table

* 🖍 apply feedback

* ✨ make style

* 🖍 minor fix in code snippet
 2023-03-06 13:44:30 -08:00
Steven Liu
7004ff55d5 [docs] Move relevant code for text2image to docs (#2537) 
* move relevant code from text2image on GitHub to docs

* 🖍 add inference for text2image with flax

* 🖍 apply feedback
 2023-03-06 13:43:45 -08:00