tripo3d/triposplat

TripoSplat is an open-source model from TripoAI / VAST AI Research that converts a single 2D image into high-quality 3D Gaussians using a novel learned density-control approach

Inference

Commercial use

Schema

LLMs

Playground API Examples

Input

Image Url*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "model_mesh": {
    "url": "https://v3b.fal.media/files/b/0a9cda42/k38FWXKPgicyd-HaLCrgf_output.ply",
    "content_type": "application/octet-stream",
    "file_name": "output.ply",
    "file_size": 17826208
  },
  "preprocessed_image": {
    "url": "https://v3b.fal.media/files/b/0a9cda42/XAzTWyWUTGkbcBGJLseH1_76a2c4d284e549279c55170e6dfc4c7e.png",
    "content_type": "image/png",
    "file_name": "76a2c4d284e549279c55170e6dfc4c7e.png",
    "file_size": 1004820,
    "width": 1024,
    "height": 1024
  },
  "num_gaussians": 262144,
  "seed": 1140533137,
  "timings": {
    "inference": 4.704996989999927,
    "export": 0.7896510509999644
  }
}

Your request will cost $0.05 per generation.

tripo3d/triposplat

Input

Result

What would you like to do next?

Logs