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
2,692 Commits 742 Branches 94 Tags
79ef9e528cd2ae8dc49c75eeb1ea5d0d17ac9d45
Commit Graph

2692 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
manosplitsis
79ef9e528c Fixed multi-token textual inversion training (#4452) 
* added placeholder token concatenation during training

* Update examples/textual_inversion/textual_inversion.py

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

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-04 12:21:31 +02:00
Dhruv Nair
801a5e2199 Cleanup Pass on flaky slow tests for Stable Diffusion (#4455) 
* lower num inference steps and precision checkk

* fix flaky inpaint tests

* remove unsued imports

* set unet default attn processor
 2023-08-04 10:24:56 +02:00
YiYi Xu
1edd0debaa fix-format (#4458) 
make style

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-08-03 20:34:37 -07:00
YiYi Xu
29ece0db79 a few fix for kandinsky combined pipeline (#4352) 
* add xformer

* enable_sequential_cpu_offload

* style

* Update src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py

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

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-08-03 15:10:41 -10:00
Patrick von Platen
1a8843f93e add sdxl to prompt weighting (#4439) 
* add sdxl to prompt weighting

* Update docs/source/en/using-diffusers/weighted_prompts.md

* Update docs/source/en/using-diffusers/weighted_prompts.md

* add sdxl to prompt weighting

* Apply suggestions from code review

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

* Apply suggestions from code review

* Update docs/source/en/using-diffusers/weighted_prompts.md

* Apply suggestions from code review

* correct

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-08-03 21:41:48 +02:00
JinK
e391b789ac Support different strength for Stable Diffusion TensorRT Inpainting pipeline (#4216) 
* Support different strength

* run make style
 2023-08-03 21:32:44 +02:00
VV-A-VV
d0b8de1262 Delete the duplicate code for the contolnet img 2 img (#4411) 
delete the duplicated code from the controlnet-img-2-img pipelines
 2023-08-03 20:32:03 +02:00
Yuyang Zhao
b9058754c5 Fix bug caused by typo (#4357) 
Fix the typo that causes `omegaconf.errors.ConfigAttributeError: Missing key parms`
 2023-08-03 20:27:42 +02:00
Alan Ji
777becda6b fix typo to ensure make test-examples work correctly (#4329) 
fix typo to ensure `make test-examples` work correctly
 2023-08-03 20:17:48 +02:00
cmdr2
380bfd82c1 Allow controlnets to be loaded (from ckpt) in a parallel thread with a SD model (ckpt), and speed it up slightly (#4298) 
Faster controlnet model instantiation, and allow controlnets to be loaded (from ckpt) in a parallel thread with a SD model (ckpt) without  tensor errors (race condition)
 2023-08-03 20:11:13 +02:00
Steven Liu
5989a85edb [docs] Distilled SD (#4442) 
* first draft

* add blog link
 2023-08-03 11:03:42 -07:00
Levi McCallum
4188f3063a Add rank argument to train_dreambooth_lora_sdxl.py (#4343) 
* Add rank argument to train_dreambooth_lora_sdxl.py

* Update train_dreambooth_lora_sdxl.py
 2023-08-03 23:27:30 +05:30
George He
0b4430e840 Fix typerror in pipeline handling for MultiControlNets which only contain a single ControlNet (#4454) 
* Handle single controlnet in multicontrolnet

* Fix formatting
 2023-08-03 17:37:07 +02:00
Patrick von Platen
a74c995e7d make style 2023-08-03 14:45:06 +00:00
Neil Wang
85aa673bec auto type conversion (#4270) 
* type conversion

Default value of `control_guidance_start` and `control_guidance_end` in `StableDiffusionControlNetPipeline.check_inputs` causes `TypeError: object of type 'float' has no len()`

Proposed fix: 
Convert `control_guidance_start` and `control_guidance_end` to list if float

* Update src/diffusers/pipelines/controlnet/pipeline_controlnet.py

* Update src/diffusers/pipelines/controlnet/pipeline_controlnet.py

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

* Update src/diffusers/pipelines/controlnet/pipeline_controlnet.py

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

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-03 16:44:48 +02:00
Dhruv Nair
1d2587bb34 move tests to nightly (#4451) 
* move tests to nightly

* clean up code quality issues

* more clean up
 2023-08-03 15:25:28 +02:00
Patrick von Platen
372b58108e fix make style 2023-08-03 10:17:00 +00:00
w4ffl35
45171174b8 Prevent online access when desired when using download_from_original_stable_diffusion_ckpt (#4271) 
Prevent online access when desired

- Bypass requests with config files option added to download_from_original_stable_diffusion_ckpt
- Adds local_files_only flags to all from_pretrained requests
 2023-08-03 12:16:41 +02:00
cmdr2
4c4fe042a7 Accept pooled_prompt_embeds in the SDXL Controlnet pipeline. Fixes an error if prompt_embeds are passed. (#4309) 
* Accept pooled_prompt_embeds in the SDXL Controlnet pipeline. Fixes an error if prompt_embeds are passed.

* Add a test for pooled prompt embeds
 2023-08-03 13:05:19 +05:30
Will Berman
47bf8e566c can call encode_prompt with out setting a text encoder instance variable (#4396) 
* can call encode_prompt with out setting a text encoder instance variable

* fix
 2023-08-02 21:25:30 -07:00
Sayak Paul
18fc40c169 [Feat] add tiny Autoencoder for (almost) instant decoding (#4384) 
* add: model implementation of tiny autoencoder.

* add: inits.

* push the latest devs.

* add: conversion script and finish.

* add: scaling factor args.

* debugging

* fix denormalization.

* fix: positional argument.

* handle use_torch_2_0_or_xformers.

* handle post_quant_conv

* handle dtype

* fix: sdxl image processor for tiny ae.

* fix: sdxl image processor for tiny ae.

* unify upcasting logic.

* copied from madness.

* remove trailing whitespace.

* set is_tiny_vae = False

* address PR comments.

* change to AutoencoderTiny

* make act_fn an str throughout

* fix: apply_forward_hook decorator call

* get rid of the special is_tiny_vae flag.

* directly scale the output.

* fix dummies?

* fix: act_fn.

* get rid of the Clamp() layer.

* bring back copied from.

* movement of the blocks to appropriate modules.

* add: docstrings to AutoencoderTiny

* add: documentation.

* changes to the conversion script.

* add doc entry.

* settle tests.

* style

* add one slow test.

* fix

* fix 2

* fix 2

* fix: 4

* fix: 5

* finish integration tests

* Apply suggestions from code review

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

* style

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-08-02 23:58:05 +05:30
Xin Kong
615c04db15 [Pipelines] Add community pipeline for Zero123 (#4295) 
* add zero123 pipeline to community

* add community doc

* reformat

* update zero123 pipeline, including cc_projection within diffusers; add convert ckpt scripts; support diffusers weights
 2023-08-02 19:36:49 +02:00
Steven Liu
ae82a3eb34 [docs] AutoPipeline tutorial (#4273) 
* first draft

* tidy api

* apply feedback

* mdx to md

* apply feedback

* Apply suggestions from code review

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

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-02 10:32:02 -07:00
Sayak Paul
816ca0048f [LoRA] Fix SDXL text encoder LoRAs (#4371) 
* temporarily disable text encoder loras.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debbuging.

* modify doc.

* rename tests.

* print slices.

* fix: assertions

* Apply suggestions from code review

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

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-02 17:00:56 +05:30
Sayak Paul
fef8d2f726 remove mentions of textual inversion from sdxl. (#4404) 2023-08-02 15:29:46 +05:30
Ella Charlaix
579b4b2020 Update documentation (#4422) 
* update documentation

* minor
 2023-08-02 11:49:22 +02:00
Steven Liu
6c5bd2a38d [docs] Fix SDXL docstring (#4397) 
fix guidance scale value
 2023-08-01 16:40:15 -07:00
Will Berman
160474ac61 train dreambooth fix pre encode class prompt (#4395) 2023-08-01 12:00:05 -07:00
YiYi Xu
c10861ee1b fix test_float16_inference (#4412) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-08-01 07:49:50 -10:00
YiYi Xu
94b332c476 support from_single_file for SDXL inpainting (#4408) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-08-01 07:47:22 -10:00
Dhruv Nair
6f4355f89f Cleanup pass for flaky Slow Tests for Stable diffusion (#4415) 
* update expected slice so img2img compile tests pass

* use default attn processor

* use default attn processor and update expected slice value to pass test

* use default attn processor

* set default attn processor and update expected slice

* set default attn processor and change precision for check

* set unet to use default attn processor
 2023-08-01 18:21:14 +02:00
estelleafl
05a1cb902c [ldm3d] documentation fixing typos (#4284) 
* fixed typo

* updated doc to be consistent in naming

* make style/quality

* preprocessing for 4 channels and not 6

* make style

* test for 4c

* make style/quality

* fixed test on cpu

* fixed doc typo

* changed default ckpt to 4c

* Update pipeline_stable_diffusion_ldm3d.py

---------

Co-authored-by: Aflalo <estellea@isl-iam1.rr.intel.com>
Co-authored-by: Aflalo <estellea@isl-gpu33.rr.intel.com>
Co-authored-by: Aflalo <estellea@isl-gpu38.rr.intel.com>
 2023-08-01 09:03:29 -07:00
Patrick von Platen
c69526a3d5 [AutoPipeline] Correct naming (#4420) 2023-08-01 14:56:27 +02:00
Nishant Rajadhyaksha
6c49d542a3 Update docs of unet_1d.py (#4394) 
Update unet_1d.py

highlighting the way the modules are actually fed in the main code as the order matters because no skip block attaches time embeds whilst others do not
 2023-07-31 11:04:47 -07:00
Sayak Paul
ba43ce3476 minor doc fixes. (#4380) 2023-07-31 12:15:56 +05:30
Andrey Voroshilov
ea5b0575f8 Clean up duplicate lines in encode_prompt (#4369) 
* Clean up duplicate line

* Clean up duplicate lines

* Clean up duplicate line
 2023-07-30 15:49:46 +05:30
Patrick von Platen
4f986fb28a [SDXL] Fix dummy imports incorrect naming (#4370) 
[SDXL] Fix dummy imports
 2023-07-30 12:17:38 +02:00
Harutatsu Akiyama
aae27262f4 [SDXL-IP2P] Add gif for demonstrating training processes (#4342) 
* [SDXL-IP2P] Add gif for demonstrating training processes

* [SDXL-IP2P] Add gif for demonstrating training processes

* [SDXL-IP2P] Change gif to URLs

* [SDXL-IP2P] Add URLs in case gif now show

---------

Co-authored-by: Harutatsu Akiyama <kf.zy.qin@gmail.com>
 2023-07-30 10:07:10 +05:30
Sayak Paul
34b5b63bb8 Update README.md to have PyPI-friendly path (#4351) 2023-07-29 08:59:18 +05:30
Will Berman
2b1786735e fix fp type in t2i adapter docs (#4350) 2023-07-28 13:01:52 -07:00
Sayak Paul
4a4cdd6b07 [Feat] Support SDXL Kohya-style LoRA (#4287) 
* sdxl lora changes.

* better name replacement.

* better replacement.

* debugging

* debugging

* debugging

* debugging

* debugging

* remove print.

* print state dict keys.

* print

* distingisuih better

* debuggable.

* fxi: tyests

* fix: arg from training script.

* access from class.

* run style

* debug

* save intermediate

* some simplifications for SDXL LoRA

* styling

* unet config is not needed in diffusers format.

* fix: dynamic SGM block mapping for SDXL kohya loras (#4322)

* Use lora compatible layers for linear proj_in/proj_out (#4323)

* improve condition for using the sgm_diffusers mapping

* informative comment.

* load compatible keys and embedding layer maaping.

* Get SDXL 1.0 example lora to load

* simplify

* specif ranks and hidden sizes.

* better handling of k rank and hidden

* debug

* debug

* debug

* debug

* debug

* fix: alpha keys

* add check for handling LoRAAttnAddedKVProcessor

* sanity comment

* modifications for text encoder SDXL

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* denugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* up

* up

* up

* up

* up

* up

* unneeded comments.

* unneeded comments.

* kwargs for the other attention processors.

* kwargs for the other attention processors.

* debugging

* debugging

* debugging

* debugging

* improve

* debugging

* debugging

* more print

* Fix alphas

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* clean up

* clean up.

* debugging

* fix: text

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Batuhan Taskaya <batuhan@python.org>
 2023-07-28 19:49:49 +02:00
Patrick von Platen
b7b6d6138d [SDXL] Make watermarker optional under certain circumstances to improve usability of SDXL 1.0 (#4346) 
* improve sdxl

* more fixes

* improve sdxl

* improve sdxl

* improve sdxl

* finish
 2023-07-28 19:29:22 +02:00
kathath
faa6cbc959 Fix repeat of negative prompt (#4335) 
fix repeat of negative prompt
 2023-07-28 18:14:22 +02:00
Patrick von Platen
306a7bd047 [ONNX] Don't download ONNX model by default (#4338) 
* [Download] Don't download ONNX weights by default

* [Download] Don't download ONNX weights by default

* [Download] Don't download ONNX weights by default

* fix more

* finish

* finish

* finish
 2023-07-28 14:02:48 +02:00
Tanupriya Singh
c7250f2b8a correct doc string for default value of guidance_scale (#4339) 2023-07-28 13:54:28 +02:00
Patrick von Platen
18b018c864 [SDXL Refiner] Fix refiner forward pass for batched input (#4327) 
* fix_batch_xl

* Fix other pipelines as well

* up

* up

* Update tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_inpaint.py

* sort

* up

* Finish it all up Co-authored-by: Bagheera <bghira@users.github.com>

* Co-authored-by: Bagheera bghira@users.github.com

* Co-authored-by: Bagheera <bghira@users.github.com>

* Finish it all up Co-authored-by: Bagheera <bghira@users.github.com>
 2023-07-28 12:34:18 +02:00
Sayak Paul
54fab2cd5f Update README_sdxl.md to correct the header (#4330) 
Update README_sdxl.md
 2023-07-28 09:22:14 +05:30
Sayak Paul
961173064d Honor the SDXL 1.0 licensing from the training scripts. (#4319) 
* honor the original license.

* train_instruct_pix2pix_xl -> train_instruct_pix2pix_sdxl
 2023-07-28 01:28:36 +05:30
Sayak Paul
7d0d073261 [Tests] add test for pipeline import. (#4276) 
* add test for pipeline import.

* Update tests/others/test_dependencies.py

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

* address suggestions

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-07-28 00:08:15 +05:30
Xinyang Li
01b6ec21fa fix validation option for dreambooth training example (#4317) 2023-07-27 09:58:52 -07:00