tencent/hunyuan-3d/v2/multi-view
Hunyuan 3d V2 Multi View by Tencent - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runtencent/hunyuan-3d/v2/multi-viewInput Schema
8 parameters · 0 required · 8 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
seed | integer | Optional | The same seed and the same prompt given to the same version of the model will output the same image every time. |
textured_mesh | boolean | Optional | If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh. · Default: false |
back_image_url | string | Optional | URL of image to use while generating the 3D model. |
guidance_scale | number | Optional | Guidance scale for the model. · Min: 0 · Max: 20 · Default: 7.5 |
left_image_url | string | Optional | URL of image to use while generating the 3D model. |
front_image_url | string | Optional | URL of image to use while generating the 3D model. |
octree_resolution | integer | Optional | Octree resolution for the model. · Min: 1 · Max: 1024 · Default: 256 |
num_inference_steps | integer | Optional | Number of inference steps to perform. · Min: 1 · Max: 50 · Default: 50 |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "tencent/hunyuan-3d/v2/multi-view",
"textured_mesh": false,
"back_image_url": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v2/multi-view/input_back_image_url_2.png",
"guidance_scale": 7.5,
"left_image_url": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v2/multi-view/input_left_image_url_0.png",
"front_image_url": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v2/multi-view/input_front_image_url_1.png",
"octree_resolution": 256,
"num_inference_steps": 50,
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Hunyuan3D
Hunyuan3D occupies a clearly bounded position in a image production pipeline under the route tencent/hunyuan-3d/v2/multi-view. It is best evaluated as a named workflow endpoint rather than as a generic substitute for neighboring versions: planners can assign the route to a specific brief, record the chosen revision, and keep approval history tied to one predictable integration surface from intake through delivery.
A practical rollout of Hunyuan3D should begin with source-readiness checks, ownership of the submitted material, an agreed budget, and a written definition of the final multi view deliverable. Before automation is enabled, the acceptance pass should verify that the returned asset opens correctly, fits the intended downstream toolchain, satisfies the project’s review criteria, and can be reproduced from the stored request and route identity tencent/hunyuan-3d/v2/multi-view.
Highlights
- Distinct output behavior. For Hunyuan3D, for Hunyuan3D, supply front, back, and left pictures of the same object In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with seed as a relevant request control; the seed control exposes the corresponding choice in this route; the seed control exposes the corresponding choice in this route.
- Creative control. For Hunyuan3D, for Hunyuan3D, combine those views into an image-derived 3D asset In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with textured mesh as a relevant request control; the textured mesh control exposes the corresponding choice in this route; the textured mesh control exposes the corresponding choice in this route.
- Workflow fit. For Hunyuan3D, for Hunyuan3D, set guidance, select between 1 and 50 iterations, and raise octree resolution as far as 1,024 In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with back image url as a relevant request control; the back image url control exposes the corresponding choice in this route; the back image url control exposes the corresponding choice in this route.
- Production detail. For Hunyuan3D, for Hunyuan3D, select white mesh by default or request the priced textured mode In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with guidance scale as a relevant request control; the guidance scale control exposes the corresponding choice in this route; the guidance scale control exposes the corresponding choice in this route.
Pricing
| Configuration | Price |
|---|---|
| Per request | $0.017 |
When to Use
| Scenario | Why this model fits |
|---|---|
| Choose Hunyuan3D | Use it when the required deliverable is specifically the image result documented for tencent/hunyuan-3d/v2/multi-view. |
| Match the source material | Select this route when your inputs naturally map to seed, textured_mesh, back_image_url, guidance_scale. |
| Use its distinguishing capability | For Hunyuan3D, supply front, back, and left pictures of the same object In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with seed as a relevant request control; the seed control exposes the corresponding choice in this route |
| Plan repeatable production | For Hunyuan3D, combine those views into an image-derived 3D asset In Hunyuan3D, this capability is applied through the exact tencent/hunyuan-3d/v2/multi-view workflow with textured mesh as a relevant request control; the textured mesh control exposes the corresponding choice in this route |
| Confirm cost and delivery | Use the pricing combinations below and the output contract above when budgeting or automating Hunyuan3D jobs. |
Prompt Guide
Build the request around the exact tencent/hunyuan-3d/v2/multi-view schema. Start with required fields, then add only the controls needed for the intended output; keep URLs reachable and enum values exactly as shown in Technical Specs.
{
"seed": 0,
"textured_mesh": false,
"back_image_url": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v2/multi-view/input_back_image_url_2.png",
"guidance_scale": 7.5
}
Technical Specs
| Specification | Value |
|---|---|
| Model ID | tencent/hunyuan-3d/v2/multi-view |
| Execution mode | async |
| Required inputs | None marked required |
| Request fields | seed (integer, optional); textured_mesh (boolean, optional); back_image_url (string, optional); guidance_scale (number, optional, min 0, max 20); left_image_url (string, optional); front_image_url (string, optional); octree_resolution (integer, optional, min 1, max 1024); num_inference_steps (integer, optional, min 1, max 50) |
| Output | url (string); content_type (string) |