Skip to content

Commit

Permalink
update README
Browse files Browse the repository at this point in the history
  • Loading branch information
kohya-ss committed May 19, 2024
1 parent 38e4c60 commit 4c79812
Showing 1 changed file with 7 additions and 1 deletion.
8 changes: 7 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -165,11 +165,14 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
- Specify the learning rate and dim (rank) for each block.
- See [Block-wise learning rates in LoRA](./docs/train_network_README-ja.md#階層別学習率) for details (Japanese only).

- Negative learning rates can now be specified during SDXL model training. PR [#1277](https://github.com/kohya-ss/sd-scripts/pull/1277) Thanks to Cauldrath!
- The model is trained to move away from the training images, so the model is easily collapsed. Use with caution. A value close to 0 is recommended.

- Training scripts can now output training settings to wandb or Tensor Board logs. Specify the `--log_config` option. PR [#1285](https://github.com/kohya-ss/sd-scripts/pull/1285) Thanks to ccharest93, plucked, rockerBOO, and VelocityRa!
- Some settings, such as API keys and directory specifications, are not output due to security issues.

- The ControlNet training script `train_controlnet.py` for SD1.5/2.x was not working, but it has been fixed. PR [#1284](https://github.com/kohya-ss/sd-scripts/pull/1284) Thanks to sdbds!

- An option `--disable_mmap_load_safetensors` is added to disable memory mapping when loading the model's .safetensors in SDXL. PR [#1266](https://github.com/kohya-ss/sd-scripts/pull/1266) Thanks to Zovjsra!
- It seems that the model file loading is faster in the WSL environment etc.
- Available in `sdxl_train.py`, `sdxl_train_network.py`, `sdxl_train_textual_inversion.py`, and `sdxl_train_control_net_lllite.py`.
Expand Down Expand Up @@ -214,6 +217,9 @@ https://github.com/kohya-ss/sd-scripts/pull/1290) Thanks to frodo821!
- ブロックごとに学習率および dim (rank) を指定することができます。
- 詳細は [LoRA の階層別学習率](./docs/train_network_README-ja.md#階層別学習率) をご覧ください。

- `sdxl_train.py` での SDXL モデル学習時に負の学習率が指定できるようになりました。PR [#1277](https://github.com/kohya-ss/sd-scripts/pull/1277) Cauldrath 氏に感謝します。
- 学習画像から離れるように学習するため、モデルは容易に崩壊します。注意して使用してください。0 に近い値を推奨します。

- 各学習スクリプトで学習設定を wandb や Tensor Board などのログに出力できるようになりました。`--log_config` オプションを指定してください。PR [#1285](https://github.com/kohya-ss/sd-scripts/pull/1285) ccharest93 氏、plucked 氏、rockerBOO 氏および VelocityRa 氏に感謝します。
- API キーや各種ディレクトリ指定など、一部の設定はセキュリティ上の問題があるため出力されません。

Expand Down

0 comments on commit 4c79812

Please sign in to comment.