gfodor / text2vox

Generates MagicaVoxel VOX models, using flux dev + hunyuan3d-2. Can generate high detail and low detail models at varying resolutions.

  • Public
  • 106 runs
  • A100 (80GB)
  • GitHub
  • License

Input

*string
Shift + Return to add a new line

Prompt for generated image

string

Detail level. High will try to generate a good high resolution voxel model, and low try to generate a good low resolution voxel model.

Default: "high"

boolean

Remove the background from the generated image. Useful to turn off if you want to generate a full voxel scene.

Default: true

integer

Random seed

Default: 1234

integer
(minimum: 1, maximum: 50)

Number of inference steps for Flux

Default: 50

number
(minimum: 0, maximum: 10)

Guidance scale for Flux

Default: 6

number
(minimum: 0, maximum: 1)

Prompt strength for img2img in Flux (only applicable if image is provided)

Default: 0.8

integer
(minimum: 20, maximum: 50)

Number of inference steps for Hunyuan

Default: 50

number
(minimum: 1, maximum: 20)

Guidance scale for Hunyuan

Default: 5.5

integer

Octree resolution for Hunyuan

Default: 512

Output

Generated in

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.