Chen Hou comments

Results 8 comments of


                                            Chen Hou

Would you please share discriminator's weight also?

Want it too, could anyone share the discriminator weights?

This Error with AutoEncoder started happening just hours ago

use vae.encode(x).latent_dist.sample() might just work

I have some doubts about "if rot90: img = img.transpose(1, 0, 2)".

Yeah, you're right, it's a flip over diagonal, but I think it can be seen as a kind of 90 degrees rotation.

editing specific input image

you can set --config to custom, and rewrite the custom config and a dataloader for it in data_utils.py then you can train on single image instead of pre-defined dataset

How long does it take to finish the whole process?

Hi! I met the same problem, I work on one single 3090ti, the mem is increasing very slowly, and after a very long time it haven't finihsed yet, I wonder...

ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 0 is different from 3)

It seems that no 3d point in last few frames, could it be the camera motion too drastic so no points are matched?

Request the support for FastVideo

Thanks! FastVideo is much more faster than Wan.

[Bug] size mismatch for FastWan2.2-TI2V-5B-FullAttn-Diffusers

And also, is that FastWan2.2-TI2V-5B-FullAttn-Diffusers actually doesn't support IT2V but only T2V?