VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
Kohya S
2024-09-26 21:37:40 +09:00
parent a94bc84dec
commit ce49ced699
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -140,9 +140,12 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
### Working in progress ### Working in progress
- __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries. - __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.
- transformers, accelerate and huggingface_hub are updated. - bitsandbytes, transformers, accelerate and huggingface_hub are updated.
- If you encounter any issues, please report them. - If you encounter any issues, please report them.
- `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!
- There is no abbreviation, so please specify the full path like `--optimizer_type bitsandbytes.optim.AdEMAMix8bit` (not bnb but bitsandbytes).
- Fixed a bug in the cache of latents. When `flip_aug`, `alpha_mask`, and `random_crop` are different in multiple subsets in the dataset configuration file (.toml), the last subset is used instead of reflecting them correctly. - Fixed a bug in the cache of latents. When `flip_aug`, `alpha_mask`, and `random_crop` are different in multiple subsets in the dataset configuration file (.toml), the last subset is used instead of reflecting them correctly.
- Fixed an issue where the timesteps in the batch were the same when using Huber loss. PR [#1628](https://github.com/kohya-ss/sd-scripts/pull/1628) Thanks to recris! - Fixed an issue where the timesteps in the batch were the same when using Huber loss. PR [#1628](https://github.com/kohya-ss/sd-scripts/pull/1628) Thanks to recris!