Zhu Yimin
Zhu Yimin
I have the same question. In my prompts, the number 49407 mean the end token of each prompt, not the useful meaning of each token. for example, [49406, 518, 34606,...
I am also interested in the training porcess. The kernel and x are trained by diffsuion model respectively. That means before training diffusion model, we need some paired kernel and...
i think it may work, cuz we only need sampled x_{t-1}, the gradient, and predicted x_0 from noise