Tripo3d H3.1 Text To 3d
Playground
Try it on WavespeedAI!Tripo3D H3.1 Text-to-3D generates high-quality 3D models from text descriptions. Supports textures with standard and HD quality, PBR materials, detailed geometry, quad mesh topology, and auto-sizing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Tripo3D H3.1 Text-to-3D
Tripo3D H3.1 Text-to-3D generates a production-ready 3D model directly from a text description. Describe the object you want — the model creates accurate geometry with optional PBR textures, quad mesh topology, and detailed quality tiers for both geometry and texture. No reference image needed.
- Have a reference photo? Try Tripo3D H3.1 Image-to-3D for more accurate results.
Why Choose This?
-
Text-driven 3D generation Create 3D models from natural language descriptions alone — no photography or reference images required.
-
Negative prompt support Specify features to avoid in the generated model for more precise control over the output geometry and style.
-
PBR material generation Generate Physically Based Rendering materials alongside the mesh for realistic real-time rendering in game engines and 3D tools.
-
Geometry and texture quality tiers Choose between standard and detailed quality independently for geometry and texture.
-
Quad mesh support Generate quad (4-sided) mesh topology instead of triangles for cleaner topology compatible with animation and sculpting workflows.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the 3D object to generate. Max 1024 characters. |
| negative_prompt | No | Features to avoid in the generated model. Max 1024 characters. |
| texture | No | Whether to generate textures for the model. Default: true. |
| pbr | No | Whether to generate PBR materials. Requires texture to be enabled. Default: true. |
| texture_quality | No | Texture quality: standard (default) or detailed (higher resolution). |
| geometry_quality | No | Geometry quality: standard (default) or detailed. |
| auto_size | No | Auto-scale the model to real-world dimensions. Default: false. |
| quad | No | Generate quad mesh topology instead of triangles. Default: false. |
How to Use
- Write your prompt — describe the object in detail including shape, material, style, and any distinctive features. Max 1024 characters.
- Add negative prompt (optional) — specify features or styles you want to avoid.
- Configure texture settings (optional) — enable or disable texture and PBR generation, and choose standard or detailed texture quality.
- Set geometry quality (optional) — choose standard for faster results or detailed for higher fidelity.
- Enable quad mesh (optional) — use quad topology for animation or sculpting workflows.
- Submit — generate and download your 3D model.
Pricing
| Texture | Texture Quality | Geometry Quality | Quad | Cost |
|---|---|---|---|---|
| No | — | Standard | No | $0.10 |
| No | — | Detailed | No | $0.30 |
| Yes | Standard | Standard | No | $0.20 |
| Yes | Standard | Detailed | No | $0.40 |
| Yes | Detailed | Standard | No | $0.30 |
| Yes | Detailed | Detailed | No | $0.50 |
Add +$0.05 to any combination above when quad is enabled.
Billing Rules
- Base: $0.10 × texture multiplier (no texture: ×1, standard texture: ×2, detailed texture: ×3)
- Detailed geometry surcharge: +$0.20
- Quad surcharge: +$0.05
- Default configuration (texture standard, geometry standard, no quad): $0.20
Best Use Cases
- Concept art & prototyping — Rapidly generate 3D assets from written descriptions for ideation and visualization.
- Game asset creation — Create textured 3D props and objects from descriptive prompts without photography.
- Animation & VFX — Use quad mesh output for animation-ready topology compatible with rigging and sculpting.
- AR/VR content — Generate PBR-textured models for immersive application development.
- Developer workflows — Embed text-driven 3D generation into creative pipelines and tools.
Pro Tips
- Be specific and descriptive in your prompt — include shape, material, style, color, and any distinctive features.
- Use negative_prompt to avoid unwanted stylistic elements or geometric artifacts.
- Use detailed geometry quality for complex shapes with fine surface detail.
- Use quad mesh when the model will be used for animation or further sculpting in tools like Blender or ZBrush.
- For objects with a known visual reference, consider using Image-to-3D for more accurate results.
Notes
- Only prompt is required; all other parameters are optional.
- Prompt and negative_prompt are each limited to 1024 characters.
- Please ensure your content complies with Tripo3D’s usage policies.
Related Models
- Tripo3D H3.1 Image-to-3D — Generate 3D models from a single reference image.
- Tripo3D H3.1 Multiview-to-3D — Higher accuracy reconstruction from 2–4 reference images.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/tripo3d/h3.1/text-to-3d" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"texture": true,
"pbr": true,
"texture_quality": "standard",
"geometry_quality": "standard",
"auto_size": false,
"quad": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text description of the 3D object to generate. Maximum 1024 characters. | |
| negative_prompt | string | No | - | Text describing features to avoid in the generated model.Maximum 1024 characters. | |
| texture | boolean | No | true | - | Whether to generate textures for the model. |
| pbr | boolean | No | true | - | Whether to generate PBR (Physically Based Rendering) materials. If true, texture is also enabled. |
| texture_quality | string | No | standard | standard, detailed | Quality level for textures. 'detailed' produces higher-resolution textures. |
| geometry_quality | string | No | standard | standard, detailed | Quality level for geometry. |
| auto_size | boolean | No | false | - | Auto-scale the model to real-world dimensions. |
| quad | boolean | No | false | - | Generate quad (4-sided) mesh topology instead of triangles. |
| face_limit | integer | No | - | 1000 ~ 2000000 | Target number of faces for the generated mesh. If not set, the model adaptively determines the count. |
| model_seed | integer | No | - | - | Seed for geometry generation reproducibility. |
| image_seed | integer | No | - | - | Seed for the text-to-image step. |
| texture_seed | integer | No | - | - | Seed for texture generation reproducibility. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |