theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 18:28:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix qwen_rope

Browse Source
This commit is contained in:
mi804
2025-08-18 17:31:18 +08:00
parent ad1da43476
commit d93de98a21
8 changed files with 36 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/qwen_image/README_zh.md
View File

@@ -236,7 +236,6 @@ Qwen-Image 系列模型训练通过统一的 [`./model_training/train.py`](./mod
* `--model_paths`: 要加载的模型路径。JSON 格式。
* `--model_id_with_origin_paths`: 带原始路径的模型 ID，例如 Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors。用逗号分隔。
* `--tokenizer_path`: tokenizer 路径，留空将会自动下载。
* `--edit_model`：是否使用 Qwen-Image-Edit。若为 True，则将使用该模型进行图像编辑。
* `--processor_path`：Qwen-Image-Edit 的 processor 路径。留空则自动下载。
* 训练
* `--learning_rate`: 学习率。