fire / trellis

For the paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

  • Public
  • 210 runs
  • L40S
  • GitHub
  • Paper
  • License

Input

*file[]

List of input images to generate 3D asset from

integer

Random seed for generation

Default: 0

boolean

Randomize seed

Default: true

boolean

Generate color video render

Default: true

boolean

Generate normal video render

Default: false

boolean

Generate 3D model file (GLB)

Default: false

boolean

Save Gaussian point cloud as PLY file

Default: false

boolean

Return the preprocessed images without background

Default: false

number
(minimum: 0, maximum: 10)

Stage 1: Sparse Structure Generation - Guidance Strength

Default: 7.5

integer
(minimum: 1, maximum: 50)

Stage 1: Sparse Structure Generation - Sampling Steps

Default: 12

number
(minimum: 0, maximum: 10)

Stage 2: Structured Latent Generation - Guidance Strength

Default: 3

integer
(minimum: 1, maximum: 50)

Stage 2: Structured Latent Generation - Sampling Steps

Default: 12

number
(minimum: 0, maximum: 0.98)

GLB Extraction - Mesh Simplification (only used if generate_model=True)

Default: 0.65

integer
(minimum: 512, maximum: 2048)

GLB Extraction - Texture Size (only used if generate_model=True)

Default: 512

Output

model_file

Loading...

no_background_image

no_background_image
Generated in

This example was created by a different version, fire/trellis:ace6e61c.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.