Hunyuan3d V2 Base

Hunyuan3d V2 Base

Playground

Hunyuan3D-V2-Base is a state-of-the-art Image-to-3D model by Tencent that turns images into 3D assets for visualization and content. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Hunyuan3D V2 Base — Image-to-3D

Hunyuan3D V2 Base is part of Tencent’s open-source Hunyuan3D-2 series — a state-of-the-art 3D generation system that transforms 2D images into high-fidelity 3D models with detailed textures. This full-featured version delivers superior quality and detail for professional 3D generation needs.

Why It Stands Out

• Single image input: Generate complete 3D models from just one 2D image.
• High-fidelity output: Produces detailed 3D models with accurate geometry and high-resolution (4K) textures.
• Superior quality: Full model capabilities for maximum detail and precision.
• Decoupled architecture: Separates geometry generation and texture synthesis for improved quality.
• Simple workflow: Just upload an image — no 3D expertise required.

Technical Highlights

The Hunyuan3D-2 system adopts a separated process of geometry generation + texture synthesis:

• Geometry Generation (Hunyuan3D-DiT): Based on a flow diffusion model that generates untextured 3D geometric models, with 2.6B parameters, capable of precisely extracting geometric information from input images.

• Texture Synthesis (Hunyuan3D-Paint): Adds high-resolution (4K) textures to geometric models, with 1.3B parameters, supporting multi-view diffusion generation technology to ensure realistic textures and consistent lighting.

By decoupling shape and texture generation, the system effectively reduces complexity and improves generation quality.

Performance and Efficiency

• High-Quality Output: Full model delivers maximum detail and texture resolution.
• Multi-modal Support: Compatible with various input methods and integrations including Blender plugins and Gradio applications.
• Open Source Ecosystem: Part of Tencent’s open-source 3D generation initiative.

Parameters

How to Use

1. Upload your image — drag and drop a file or paste a public URL.
2. Click Run and wait for the 3D model to generate.
3. Preview and download the result.

Best Use Cases

• Game Development — Generate production-ready 3D assets from concept art.
• E-commerce — Create detailed 3D product models for interactive displays.
• 3D Printing — Convert 2D designs into high-detail printable 3D models.
• AR/VR Content — Generate quality 3D objects for immersive experiences.
• Film & Animation — Create 3D assets from character designs and storyboards.
• Product Visualization — Transform product photos into interactive 3D models.

Pricing

Model Comparison

Pro Tips for Best Quality

• Use images with clear subjects against simple or transparent backgrounds.
• Front-facing or 3/4 angle views typically produce the best results.
• Ensure the subject is well-lit and clearly visible in the image.
• Higher resolution source images yield more detailed 3D models.
• For complex objects, use images that clearly show the main features.

Notes

• Ensure uploaded image URLs are publicly accessible.
• Processing time varies based on image complexity and current queue load.
• For faster, more affordable generation, consider using Hunyuan3D V2 Mini.
• Please ensure your content complies with usage guidelines.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d/v2-base" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"