Image to 3D — 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

≈ 44.811 kredi/üretim

Ayarlar

Image Urlzorunlu

URL of the input image to convert into a 3D Gaussian splat.

Num Gaussiansisteğe bağlı

Target number of Gaussians in the output splat. Higher means more detail but larger files and slower rendering. Rounded to the nearest multiple of 32 internally.

Num Inference Stepsisteğe bağlı

Number of flow-matching sampler steps. More steps improve fidelity with a roughly linear runtime cost.

Guidance Scaleisteğe bağlı

Classifier-free guidance strength. Values at or below 1.0 disable guidance; higher values increase detail and adherence to the input image, but too high can oversaturate colors.

Output Formatisteğe bağlı

File format for the generated Gaussian splat.

Seedisteğe bağlı

Random seed for reproducibility. If None, a random seed is generated.

Enable Safety Checkeristeğe bağlı

Enable safety checking of the input image.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.