v21.6.4

What's Changed

• Fix setup logic... again by @bmaltais in #895

Full Changelog: v21.6.3...v21.6.4

v21.6.3

What's Changed

• Fix setup logic by @bmaltais in #894

Full Changelog: v21.6.2...v21.6.3

v21.6.2

What's Changed

• Fix issue with torch version by @bmaltais in #891

Full Changelog: v21.6.1...v21.6.2

v21.6.1

• Add detection of files outside the venv to scripts

What's Changed

• v21.6.1 by @bmaltais in #889

Full Changelog: v21.6.0...v21.6.1

v21.6.0

• Merge kohya_ss repo changes
• Improge logging of kohya_ss GUI

What's Changed

• Downgrade bitsandbytes for Linux/Mac too by @rkfg in #885
• v21.6.0 by @bmaltais in #888

New Contributors

• @rkfg made their first contribution in #885

Full Changelog: v21.5.14...v21.6.0

v21.5.14

• 2023/05/28 (v21.5.14)

• Add Create Groupo tool and GUI
• Upgrade gradio release to fix issue with UI refresh on config load.
• D-Adaptation v3.0 is now supported. PR #530 Thanks to sdbds!
  • --optimizer_type now accepts DAdaptAdamPreprint, DAdaptAdanIP, and DAdaptLion.
  • DAdaptAdam is now new. The old DAdaptAdam is available with DAdaptAdamPreprint.
  • Simply specifying DAdaptation will use DAdaptAdamPreprint (same behavior as before).
  • You need to install D-Adaptation v3.0. After activating venv, please do pip install -U dadaptation.
  • See PR and D-Adaptation documentation for details.

v21.5.12

• Fixed several bugs.
  • The state is saved even when the --save_state option is not specified in fine_tune.py and train_db.py. PR #521 Thanks to akshaal!
  • Cannot load LoRA without alpha. PR #527 Thanks to Manjiz!
  • Minor changes to console output during sample generation. PR #515 Thanks to yanhuifair!
• The generation script now uses xformers for VAE as well.
• Fixed an issue where an error would occur if the encoding of the prompt file was different from the default. PR #510 Thanks to sdbds!
  • Please save the prompt file in UTF-8.

v21.5.11

• 2023/07/15 (v21.5.11)
  • Added an option --dim_from_weights to train_network.py to automatically determine the dim(rank) from the weight file. PR #491 Thanks to AI-Casanova!
    • It is useful in combination with resize_lora.py. Please see the PR for details.
  • Fixed a bug where the noise resolution was incorrect with Multires noise. PR #489 Thanks to sdbds!
    • Please see the PR for details.
  • The image generation scripts can now use img2img and highres fix at the same time.
  • Fixed a bug where the hint image of ControlNet was incorrectly BGR instead of RGB in the image generation scripts.
  • Added a feature to the image generation scripts to use the memory-efficient VAE.
    • If you specify a number with the --vae_slices option, the memory-efficient VAE will be used. The maximum output size will be larger, but it will be slower. Please specify a value of about 16 or 32.
    • The implementation of the VAE is in library/slicing_vae.py.
  • Fix for wandb #ebabchick
  • Added English translation of documents by darkstorm2150. Thank you very much!
  • The prompt for sample generation during training can now be specified in .toml or .json. PR #504 Thanks to Linaqruf!
    • For details on prompt description, please see the PR.

v21.5.10

Make sure to re-run .\setup.bat after pulling this release.

• 2023/04/07 (v21.5.10)
  • Fix issue #734
  • The documentation has been moved to the docs folder. If you have links, please change them.
  • DAdaptAdaGrad, DAdaptAdan, and DAdaptSGD are now supported by DAdaptation. PR#455 Thanks to sdbds!
    • DAdaptation needs to be installed. Also, depending on the optimizer, DAdaptation may need to be updated. Please update with pip install --upgrade dadaptation.
  • Added support for pre-calculation of LoRA weights in image generation scripts. Specify --network_pre_calc.
    • The prompt option --am is available. Also, it is disabled when Regional LoRA is used.
  • Added Adaptive noise scale to each training script. Specify a number with --adaptive_noise_scale to enable it.
    • Experimental option. It may be removed or changed in the future.
    • This is an original implementation that automatically adjusts the value of the noise offset according to the absolute value of the mean of each channel of the latents. It is expected that appropriate noise offsets will be set for bright and dark images, respectively.
    • Specify it together with --noise_offset.
    • The actual value of the noise offset is calculated as noise_offset + abs(mean(latents, dim=(2,3))) * adaptive_noise_scale. Since the latent is close to a normal distribution, it may be a good idea to specify a value of about 1/10 to the same as the noise offset.
    • Negative values can also be specified, in which case the noise offset will be clipped to 0 or more.
  • Other minor fixes.

v21.5.9

• 2023/04/06 (v21.5.9)

  • Implement headless mode to enable easier support under headless services like vast.ai. To make use of it start the gui with the --headless argument like:

    .\gui.ps1 --headless or .\gui.bat --headless or ./gui.sh --headless

  • Added the option for the user to put the wandb api key in a textbox under the advanced configuration dropdown and a checkbox to toggle for using wandb logging. @x-CK-x

  • Docker build image @Trojaner

    • Updated README to use docker compose run instead of docker compose up to fix broken tqdm
      • Related: Doesn't work with docker-compose tqdm/tqdm#771
    • Fixed build for latest release
    • Replace pillow with pillow-simd
    • Removed --no-cache again as pip cache is not enabled anyway

  • While overwriting .txt files with prefix and postfix including different encodings you might encounter this decoder error. This small fix gets rid of it... @ertugrul-dmr

  • Docker Add --no-cache-dir to reduce image size @chiragjn

  • Reverting bitsandbytes version to 0.35.0 due to issues with 0.38.1 on some systems