From b1e6504007aca20d15155d5c9fe880fb5e0002b8 Mon Sep 17 00:00:00 2001 From: Kohya S Date: Fri, 25 Oct 2024 18:56:25 +0900 Subject: [PATCH] update README --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index de5cddb9..ce28d004 100644 --- a/README.md +++ b/README.md @@ -143,6 +143,9 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser - bitsandbytes, transformers, accelerate and huggingface_hub are updated. - If you encounter any issues, please report them. +- Fixed a bug where the loss weight was incorrect when `--debiased_estimation_loss` was specified with `--v_parameterization`. PR [#1715](https://github.com/kohya-ss/sd-scripts/pull/1715) Thanks to catboxanon! See [the PR](https://github.com/kohya-ss/sd-scripts/pull/1715) for details. + - Removed the warning when `--v_parameterization` is specified in SDXL and SD1.5. PR [#1717](https://github.com/kohya-ss/sd-scripts/pull/1717) + - There was a bug where the min_bucket_reso/max_bucket_reso in the dataset configuration did not create the correct resolution bucket if it was not divisible by bucket_reso_steps. These values are now warned and automatically rounded to a divisible value. Thanks to Maru-mee for raising the issue. Related PR [#1632](https://github.com/kohya-ss/sd-scripts/pull/1632) - `bitsandbytes` is updated to 0.44.0. Now you can use `AdEMAMix8bit` and `PagedAdEMAMix8bit` in the training script. PR [#1640](https://github.com/kohya-ss/sd-scripts/pull/1640) Thanks to sdbds!