TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
Paper • 2502.06608 • Published • 39
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("brneo/TripoSG", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]TripoSG - High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
Model Description
Model Architecture
TripoSG utilizes a novel architecture combining:
- Rectified Flow (RF) based Transformer for stable, linear trajectory modeling
- Advanced VAE with SDF-based representation and hybrid geometric supervision
- Cross-attention mechanism for image feature condition
- 1.5B parameters operating on 2048 latent tokens
Intended Uses
This model is designed for:
- Converting single images to high-quality 3D meshes
- Creative and design applications
- Gaming and VFX asset creation
- Prototyping and visualization
Requirements
- CUDA-capable GPU (>8GB VRAM)
Usage
For detailed usage instructions, please visit our GitHub repository.
About
TripoSG is developed by Tripo, VAST AI Research, pushing the boundaries of 3D Generative AI. For more information:
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support