Open MoonBlvd opened 4 weeks ago
Thanks for your attention to our work! We apply the Classifier-free Guidance, which will use other guidance (num_cfg
) to improve the quality of images. The implementation is following instructpix2pix: https://arxiv.org/pdf/2211.09800 (see equation 3)
The method to use these cfg: https://github.com/VectorSpaceLab/OmniGen/blob/main/OmniGen/model.py#L363-L370
Thank you for the great work! I'm trying to understand the detail and found the "num_cfg" is a bit confusing to me. In pipeline code there is
and then when generating there is:
and after it's generated there is
Why do we generate 3 and only take the first sample?
Thank you for your help!