Hunyuan3d V2.1

Hunyuan3d V2.1

Playground

Tencent Hunyuan3D v2.1 is a scalable 3D asset-creation system that advances state-of-the-art 3D generation for asset workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Hunyuan3D V2.1

Hunyuan3D V2.1 is Tencent’s advanced image-to-3D generation model. Upload a single photo and the model reconstructs it as a detailed, textured 3D asset — ready for use in games, product visualization, AR/VR, and creative pipelines.

Why Choose This?

• Single-image 3D reconstruction Generate a fully textured 3D model from just one reference photo — no multi-view capture or manual modeling required.

• High geometric fidelity Accurately reconstructs object shape, surface detail, and proportions from the input image.

• Rich texture output Produces clean, high-quality textures that closely match the colors and materials in the source photo.

• Production-ready assets Output is suitable for direct use in game engines, 3D editors, and AR/VR workflows.

How to Use

1. Upload your image — provide a clear, well-lit photo of the object you want to convert to 3D.
2. Submit — the model reconstructs and textures the 3D asset automatically.
3. Download your generated 3D model.

Pricing

Just $0.40 per generation.

Best Use Cases

• Game & Interactive Media — Rapidly prototype 3D props and assets from reference photos.
• E-commerce & Product Visualization — Create 3D product models for interactive viewers and AR try-on experiences.
• AR/VR Content — Generate real-world object reconstructions for immersive applications.
• Creative & Design — Turn concept art or physical objects into editable 3D assets without manual modeling.
• Digital Twins — Quickly digitize physical objects for simulation or archival purposes.

Pro Tips

• Use a clean, well-lit photo with the object centered and clearly visible for the most accurate reconstruction.
• Plain or neutral backgrounds help the model focus on the object geometry and texture.
• Avoid heavily reflective or transparent surfaces — these are harder for single-image reconstruction to handle accurately.
• Photos taken at a slight angle (rather than perfectly flat-on) tend to produce better depth estimation.

Notes

• image is the only required field.
• Ensure image URLs are publicly accessible if using a link rather than a direct upload.
• Please ensure your content complies with WaveSpeed AI’s usage policies.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d/v2.1" \
--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}"