GOT-OCR2.0模型运行出现问题

[zjx140]

System Info / 系統信息

cuda 11.8
python 3.10
torch 2.4.0

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

xinference 1.1.0

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local --host 0.0.0.0 --port 9997

Reproduction / 复现过程

点击GOT-OCR2.0加载后点击webUI报错
内容如下
2024-12-17 00:05:53,490 xinference.core.model 1263 INFO ModelActor(GOT-OCR2_0-0) loaded 2024-12-17 00:05:53,492 xinference.core.worker 1082 INFO [request 180155f4-bbc7-11ef-9402-00ffaabbccdd] Leave launch_builtin_model, elapsed time: 228 s 2024-12-17 00:05:56,294 xinference.api.restful_api 1037 ERROR Traceback (most recent call last): File "/home/zjx140/anaconda3/envs/xinference/lib/python3.10/site-packages/xinference/api/restful_api.py", line 1180, in build_gradio_images_interface ).build() File "/home/zjx140/anaconda3/envs/xinference/lib/python3.10/site-packages/xinference/core/image_interface.py", line 59, in build assert "stable_diffusion" in self.model_family AssertionError

Expected behavior / 期待表现

希望能够打开webUI

[qinxuye]

目前 image 的 web UI 是给文生图/图生图用的，OCR 还不能用。

[github-actions]

This issue is stale because it has been open for 7 days with no activity.