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
2024-05-19 19:00:32 +09:00
parent 38e4c602b1
commit 4c798129b0
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -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. - 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). - 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! - 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. - 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! - 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! - 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. - 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`. - Available in `sdxl_train.py`, `sdxl_train_network.py`, `sdxl_train_textual_inversion.py`, and `sdxl_train_control_net_lllite.py`.
@@ -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。 - 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。 - 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。 - 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。 - 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。