Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

v21.5.8 #714

Merged
merged 52 commits into from
May 5, 2023
Merged

v21.5.8 #714

merged 52 commits into from
May 5, 2023

Conversation

bmaltais
Copy link
Owner

@bmaltais bmaltais commented May 5, 2023

  • 2023/04/05 (v21.5.8)
    • Add Cache latents to disk option to the gui.
    • When saving v2 models in Diffusers format in training scripts and conversion scripts, it was found that the U-Net configuration is different from those of Hugging Face's stabilityai models (this repository is "use_linear_projection": false, stabilityai is true). Please note that the weight shapes are different, so please be careful when using the weight files directly. We apologize for the inconvenience.
      • Since the U-Net model is created based on the configuration, it should not cause any problems in training or inference.
      • Added --unet_use_linear_projection option to convert_diffusers20_original_sd.py script. If you specify this option, you can save a Diffusers format model with the same configuration as stabilityai's model from an SD format model (a single *.safetensors or *.ckpt file). Unfortunately, it is not possible to convert a Diffusers format model to the same format.
    • Lion8bit optimizer is supported. PR #447 Thanks to sdbds!
      • Currently it is optional because you need to update bitsandbytes version. See "Optional: Use Lion8bit" in installation instructions to use it.
    • Multi-GPU training with DDP is supported in each training script. PR #448 Thanks to Isotr0py!
    • Multi resolution noise (pyramid noise) is supported in each training script. PR #471 Thanks to pamparamm!
    • Add --no-cache-dir to reduce image size @chiragjn

tomj2ee and others added 30 commits April 28, 2023 17:51
@tomj2ee
Create train_network_README-zh.md
2d369b3
@tomj2ee
Update train_network_README-zh.md
fbcf56b
@tomj2ee
Create train_db_README-zh.md
c14b093
@kohya-ss
Merge pull request #459 from tomj2ee/main
40c37b1 
train_network_README-zh.md  and  train_db_README-zh.md
@kohya-ss
add document for gen script
780c606
@kohya-ss
Merge branch 'main' into dev
ddeeb94
@kohya-ss
Update gen_img_README-ja.md
69475f5
@kohya-ss
Add images to gen_img_README-ja.md
7078e64
@kohya-ss
Update readme
ad8a593
@kohya-ss
Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev
c7dbcc6
@kohya-ss
fix typo
eaa2460
@kohya-ss
Merge pull request #467 from kohya-ss/dev
bc803e0 
add doc for gen_img
@bmaltais
Add --cache_latents_to_disk option to the GUI
856d610
@pamparamm
Multi-Resolution Noise
b18d099
@bmaltais
Add missing options to WD14 tagger
be3ba65 
Refactor code
@Trojaner
Docker: use python 3.10 and remove venv
2389dc3
@Trojaner
Docker: fix missing pip
77f1e74
@Trojaner
Docker: Fix python-tk version
1f6bef6
@Trojaner
Docker: Fix not finding accelerate command
c6e1874
@Trojaner
Install shipped torch
1f76494
@Trojaner
Docker: remove useless steps
880d8a7
@Trojaner
Docker: use python 3.8 packages for faster image build
d15c895
@Trojaner
Docker: ignore built-in deps
f4a7104
@bmaltais
Merge pull request #703 from Trojaner/feature/docker-python-3-10
4cee0e7 
Docker: Upgrade to Python 3.10 and remove venv
@sdbds
Support for Lion8bit (#447)
335b2f9 
* ADD libbitsandbytes.dll for 0.38.1

* Delete libbitsandbytes_cuda116.dll

* Delete cextension.py

* add main.py

* Update requirements.txt for bitsandbytes 0.38.1

* Update README.md for bitsandbytes-windows

* Update README-ja.md  for bitsandbytes 0.38.1

* Update main.py for return cuda118

* Update train_util.py for lion8bit

* Update train_README-ja.md for lion8bit

* Update train_util.py for add DAdaptAdan and DAdaptSGD

* Update train_util.py for DAdaptadam

* Update train_network.py for dadapt

* Update train_README-ja.md for DAdapt

* Update train_util.py for DAdapt

* Update train_network.py for DAdaptAdaGrad

* Update train_db.py for DAdapt

* Update fine_tune.py for DAdapt

* Update train_textual_inversion.py for DAdapt

* Update train_textual_inversion_XTI.py for DAdapt

* Revert "Merge branch 'qinglong' into main"

This reverts commit b65c023083d6d1e8a30eb42eddd603d1aac97650, reversing
changes made to f6fda20caf5e773d56bcfb5c4575c650bb85362b.

* Revert "Update requirements.txt for bitsandbytes 0.38.1"

This reverts commit 83abc60dfaddb26845f54228425b98dd67997528.

* Revert "Delete cextension.py"

This reverts commit 3ba4dfe046874393f2a022a4cbef3628ada35391.

* Revert "Update README.md for bitsandbytes-windows"

This reverts commit 4642c52086b5e9791233007e2fdfd97f832cd897.

* Revert "Update README-ja.md  for bitsandbytes 0.38.1"

This reverts commit fa6d7485ac067ebc49e6f381afdb8dd2f12caa8f.

* Revert "ADD libbitsandbytes.dll for 0.38.1"

This reverts commit bee1e6f731d2428dacb34b61997f06143c69c278.

* Revert "Delete libbitsandbytes_cuda116.dll"

This reverts commit 891c7e92623dab92f3767663982627cca6a26724.

* reverse main.py

* Reverse main.py
@kohya-ss
Add error message if no Lion8bit
a7485e4
@Isotr0py
Fix DDP issues and Support DDP for all training scripts (#448)
e1143ca 
* Fix DDP bugs

* Fix DDP bugs for finetune and db

* refactor model loader

* fix DDP network

* try to fix DDP network in train unet only

* remove unuse DDP import

* refactor DDP transform

* refactor DDP transform

* fix sample images bugs

* change DDP tranform location

* add autocast to train_db

* support DDP in XTI

* Clear DDP import
@kohya-ss
make transform_DDP more intuitive
2fcbfec
@kohya-ss
Merge pull request #471 from pamparamm/multires-noise
2e688b7 
Multi-Resolution Noise
@kohya-ss
Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev
6957966
kohya-ss and others added 22 commits May 3, 2023 11:31
@kohya-ss
add ja help message for mutires noise
f6556f7
@kohya-ss
explicit import for BinaryIO, will fix #405
e25164c
@kohya-ss
fix unet cfg is different in saving diffuser model
1cba447
@kohya-ss
Revert unet config, add option to convert script
758a1e7
@kohya-ss
update readme
b271a6b
@kohya-ss
Merge pull request #475 from kohya-ss/dev
2fad5b8 
unet config, lion 8bit, ddp, pyramid noise etc.
@kohya-ss
Update README.md
b9085fc
@bmaltais
Merge branch 'main' of https://github.com/kohya-ss/sd-scripts into dev
e2b5645
@bmaltais
Merge branch 'dev' of https://github.com/bmaltais/kohya_ss into dev
71f9181
@kohya-ss
raise error when both noise offset and multires
60bbe64
@kohya-ss
Merge pull request #477 from kohya-ss/dev
ad5f318 
raise error when both noise offset and multires
@bmaltais
Add support for Lion8bit
111527b
@bmaltais
Mark bitsandbytes folder as deprecated
daae65e
@bmaltais
Mark bitsandbytes as deprecated
bab827e
@bmaltais
Add multi-resolution noise training support
d3a8944
@bmaltais
Merge branch 'master' into dev
ca83de2
@ertugrul-dmr
fix for UnicodeDecodeError
4740ad0
@bmaltais
Merge pull request #711 from ertugrul-dmr/master
ba2b3ab 
Fix for UnicodeDecodeError
@bmaltais
Fix issue with noise offset
f1193ea
@bmaltais
Update some vars from str to float and int
f942783
@bmaltais
Merge branch 'main' of https://github.com/kohya-ss/sd-scripts into dev
59c5c18
@bmaltais
v21.5.8
ef28015
@bmaltais bmaltais merged commit 52dd50f into master May 5, 2023
bmaltais pushed a commit that referenced this pull request Aug 4, 2023
@kohya-ss
Merge pull request #714 from kohya-ss/dev
f4935dd 
pool output fix, v_pred loss like etc.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
8 participants
@bmaltais @tomj2ee @kohya-ss @pamparamm @Trojaner @sdbds @Isotr0py @ertugrul-dmr