sjc

sjc copied to clipboard

Hi, I fetched some generated poses by `Poser()` and some examples: ``` n_steps = 10 poser = Poser(H=128, W=256, fov=60., R=1.5) Ks, poses, prompt_prefixes = poser.sample_train(n_steps) print(Ks) print(poses) # Ks...

OrangeSodahub

How to train the model with a new dataset?

1

Dear authors, I want to explore the finetune of your model, however, I didn't find the training usage in the readme file. Can you provide the related training usage? Thank...

ShikangWen2000

In paper, page 5, (26), what dose it mean that imposes severe penalties at small weights? If weights are small, which means transparent, the shape of log(1+x) pass(0, 0) and...

Gynjn

noisy_x scaling before diffusion models

1

Hi, I noticed you apply a normalization with on noisy rendered images with a constant (1 + sigma^2). (https://github.com/pals-ttic/sjc/blob/main/adapt_sd.py#L133). I am confused with the intuition to scale the noisy data...

florinshen

Bibtex not up to date

1

nice work !

ThibaultGROUEIX

Great! Can you provide the videos like `https://dreamfusion3d.github.io/gallery.html`, so that we can better compare the performance between each algo like Magic3D?

densechen

How to get obj files

6

Hey it is a wonderful repo I wonder how I can get the output as a 3d model in the obj or fbx format

Pavankunchala

Thanks for the amazing job. When starting to train a model, after refreshing the page, the original running process cannot be found. How to find it? Run one again and...

fenglinglwb

Colab

13

Hi. Is it possible to run this code in the colab pro? Are you guys about to release some colab? Very nice work.

LucasSilvaFerreira

The next SD version could speed up the generation of 3d models ? "Stable Diffusion will generate 30 images per second instead of one image in 5.6 seconds"

1

Hi in a interview Emad say "that next week Stable Diffusion will generate 30 images per second instead of one image in 5.6 seconds" Does it's mean that sjc will...

alexfredo