mareksagan / dreamgaussian

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. Hologram optimized

  • Public
  • 350 runs
  • A100 (80GB)
  • GitHub
Iterate in playground

Input

image
file

Input image to convert to 3D

string
Shift + Return to add a new line

Text prompt to generate 3D object from

integer

Target preprocessed input image size

Default: 256

integer
(minimum: -90, maximum: 90)

Input image elevation

Default: 0

integer
(minimum: 0)

Number of iterations

Default: 500

integer
(minimum: 0)

Number of refinement iterations

Default: 50

integer
(minimum: 200, maximum: 10000)

Number of sampled points for Gaussian Splatting

Default: 1000

Output

Generated in

This output was created using a different version of the model, mareksagan/dreamgaussian:c0c69c49.

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.