zibojia comments

Results 18 comments of


                                            zibojia

Some errors in your generation code, but if you use the code from huggingface, it works well

Thanks for your reply! I have tested your pretrained model, and I found that some errors may occur in the beam search and decode process.

Some errors in your generation code, but if you use the code from huggingface, it works well

Sadly, after occupying with your codes for a couple of days. I STILL COULDN'T reimplement your results, even though I use your pretrained model.

Some errors in your generation code, but if you use the code from huggingface, it works well

After struggling of a couple of weeks, I successfully re-implement your paper! Thanks for your contribution to the community

Temporal MultiDiffusion doesn't work

We use the slidding window to inpaint the any length video. -- The author from the COCOCO.

Temporal MultiDiffusion doesn't work

> > > > Thanks for your great job! > > > > I implemented the Temporal MultiDiffusion based on the paper, but there are still significant appearance differences between...

Temporal MultiDiffusion doesn't work

We haven't tried the method used in AVID but we found slidding windows works well.

About environment setup

The environment is samilier with the AnimateDiff.

A small suggestion

Thank you! I will give more explaination soon.

When will the training code released?

We will release all source codes after this paper is accepted by a conference or journel

When will the training code released?

If you have any questions about the training process. I will discuss with you.