求助20241127视频生成模型部署过程中部署示例(CogVideoX)运行示例报错 #403

Closed
opened 2024-11-28 17:20:42 +08:00 by slxx · 3 comments

1、在autoDL上租用的3090服务器,安装顺序部署完成cogvideo后,运行示例报错python inference/cli_demo.py --model_path THUDM/CogVideoX-5b --prompt "A panda is practicing Tai Chi by the seaside" --output_path outputs/panda-taichi.mp4
image

2、安装部署 (Text2Video-Zero)模型时pip install -r requirements.txt 时一直卡住了
image

1、在autoDL上租用的3090服务器,安装顺序部署完成cogvideo后,运行示例报错python inference/cli_demo.py --model_path THUDM/CogVideoX-5b --prompt "A panda is practicing Tai Chi by the seaside" --output_path outputs/panda-taichi.mp4 ![image](/attachments/16f23ca2-fa7b-474e-9ea4-afeb95ba12dd) 2、安装部署 (Text2Video-Zero)模型时pip install -r requirements.txt 时一直卡住了 ![image](/attachments/16f3eed1-a57c-42e5-a417-8c7df9138e4c)
400 KiB
426 KiB

第一个问题,应该是CogVideo出现一点问题了,需要修改inference/cli_demo.py文件中第168行修改成parser.add_argument("--num_frames", type=int, default=48, help="Number of steps for the inference process")
或者在运行命令的最后加上 --num_frames 48

第一个问题,应该是CogVideo出现一点问题了,需要修改inference/cli_demo.py文件中第168行修改成parser.add_argument("--num_frames", type=int, default=48, help="Number of steps for the inference process") 或者在运行命令的最后加上 --num_frames 48

第二个问题,应该多等待一会儿就好了

第二个问题,应该多等待一会儿就好了
Author

谢谢,已解决

谢谢,已解决
slxx closed this issue 2024-12-03 10:43:48 +08:00
Sign in to join this conversation.
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: HswOAuth/llm_course#403
No description provided.