김재훈 (Kim Jaihoon)

Latent vector input

3

The model performs really well, and I would like to further explore its potential benefits in other domains. When input (latents) is not provided, ControlNet automatically fill in latents with...

COLMAP on synthetic dataset (white background w/ mask)

1

Hi, I have been trying to reconstruct synthetic object using COLMAP. I failed to reconstruct sparse scene even when I provided mask input images in feature matching step. I also...

> > I had the same issue just now. In my case, the problem is that I did not clear out the existing feature extracted before I add in the...

Autoencoder training details

3

Hi, I am trying to finetune Autoencoder of Stable Diffusion model. Could you please provide the details of learning rate scheduler and optimizer ? Thank you

Inconsistent channel in texture map

3

If you do not know the root cause of the problem / bug, and wish someone to help you, please post according to this template: ## 🐛 Bugs / Unexpected...

Hi, I was playing with Zero123 and noticed that the model breaks at a certain point when I generate outputs using the previously generated samples from Zero123. I doubt the...

Hi, thank you for your great work. I finetuned your model on another dataset, but it sometimes gives non-white background images. Have you applied any tricks to enforce background to...

Real time renderer

11

Hi, When I used the SIBR real time viewer, it gives me this warning. Also when I switch rendering type to Ellipsoids, the whole system seems to stop and I...

Co3D depth warping

1

Hi, I noticed that most of the logics are done using pytorch3d. I would like to plug in co3d in my project but seems like the job could be done...

Dataset index sequence_frames_in_order

3

Hi, thanks for your great work. I just finished downloading the entire dataset, but it seems like there are more sequences (36K) than reported in the paper which is 18K....