Xiwen Wu

Obviously, this error occurs since OpenCV can not be detected. The possible reasons are: ### 1.OpenCV is not installed To check if it is installed, run `pkg-config --modversion opencv` in...

currently RTX 4090 cannot satisfy the requirements for both training and inference, the potential solution would be quantization. no official official configurations or workarounds to run Open-Sora on consumer-graded gpu...

could you give me your command when you run? Is there any modifications in the inference code or config file?

Theoratically, config t2i2v_768px.py generates the best result. Could you upload your generated video or the screenshots? meanwhile you can try some other prompts to see if it is also bad

> Could you please re-clone the code and run it again according to the instructions in your README? I find it a bit puzzling. https://github.com/user-attachments/assets/e5b42be2-4e39-45b6-96cd-1784d31d0597 this is the video I...

It is supported, you may check some details here: https://github.com/hpcaitech/Open-Sora/blob/main/docs/hcae.md

> 改 file:///+文件路径 您好，我尝试输入路径 file:////home/project/debug/video/frame_0.jpg, 他还是报错Error code: 400 - {'error': {'code': 'InvalidParameter.DataInspection', 'param': None, 'message': 'The media format is not supported or incorrect for the data inspection.', 'type': 'InvalidParameter.DataInspection'},

> api形式的inference如果以输入路径形式的话file://xxx，我这边测试无论是图片还是视频文件都不行，但是通过base64或者一个网上可访问链接的方式倒是都可以 确实是，本地视频可以自行采样取帧，然后转换成base64传参数就行