Generate a detailed 3D model from a text description with configurable texture, material, geometry, scale, and mesh options.
Related Meshy 7 Models
API Examples
Submit Example
const response = await fetch('https://api.flaq.ai/api/v1/3d/task', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model_name: 'meshy-v7-text-to-3d',
prompt: 'A stylized red panda explorer wearing a small canvas backpack',
topology: 'quad',
remesh: true,
symmetry_mode: 'auto',
pose_mode: 'a-pose',
pbr: true,
texture_prompt: 'Hand-painted fur and weathered canvas with warm autumn colors',
texture_image: 'https://example.com/red-panda-texture.png',
}),
});
const { data } = await response.json();
const taskId = data.task_id;
Polling Example
// Step 2: Poll for results
const taskId = data.task_id;
const pollResult = async (taskId) => {
const res = await fetch(`https://api.flaq.ai/api/v1/3d/${taskId}`, {
headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
});
return res.json();
};
while (true) {
const pollResultData = await pollResult(taskId);
const status = pollResultData.data.task_status;
if (status === 'succeed') {
console.log(pollResultData.data.task_result.files[0].url);
break;
}
if (status === 'failed') {
console.error(pollResultData.data.task_status_msg);
break;
}
await new Promise(resolve => setTimeout(resolve, 10000));
}
Submit Example
import requests
response = requests.post(
'https://api.flaq.ai/api/v1/3d/task',
headers={
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
json={
'model_name': 'meshy-v7-text-to-3d',
'prompt': 'A stylized red panda explorer wearing a small canvas backpack',
'topology': 'quad',
'remesh': True,
'symmetry_mode': 'auto',
'pose_mode': 'a-pose',
'pbr': True,
'texture_prompt': 'Hand-painted fur and weathered canvas with warm autumn colors',
'texture_image': 'https://example.com/red-panda-texture.png',
},
)
response.raise_for_status()
task_id = response.json()['data']['task_id']
Polling Example
# Step 2: Poll for results
task_id = response.json()['data']['task_id']
poll_url = f"https://api.flaq.ai/api/v1/3d/{task_id}"
while True:
poll_result = requests.get(poll_url, headers={'Authorization': 'Bearer YOUR_API_KEY'}).json()
status = poll_result['data']['task_status']
if status == 'succeed':
print(poll_result['data']['task_result']['files'][0]['url'])
break
if status == 'failed':
print(poll_result['data']['task_status_msg'])
break
time.sleep(10)
Submit Example
curl -X POST "https://api.flaq.ai/api/v1/3d/task" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model_name": "meshy-v7-text-to-3d",
"prompt": "A stylized red panda explorer wearing a small canvas backpack",
"topology": "quad",
"remesh": true,
"symmetry_mode": "auto",
"pose_mode": "a-pose",
"pbr": true,
"texture_prompt": "Hand-painted fur and weathered canvas with warm autumn colors",
"texture_image": "https://example.com/red-panda-texture.png"
}'
Polling Example
# Step 2: Poll for results
# Replace {task_id} with the task_id returned from the submit response
curl -X GET "https://api.flaq.ai/api/v1/3d/{task_id}" \
-H "Authorization: Bearer YOUR_API_KEY"
Meshy 7 Text to 3D Pricing
| Parameters | Price | Original Price | Discount |
|---|
README
Meshy 7 Text-to-3D API (Prompt-Driven 3D Model Generation with Optional PBR)
Meshy 7 Text-to-3D API generates a 3D model from a natural-language description for game development, design exploration, digital content, and spatial applications. Developers can configure topology, target polygon count, remeshing, symmetry, humanoid pose, and optional PBR texturing. Available through Flaq AI, the model provides a flexible prompt-to-3D workflow with additional texture guidance and random seed control.
Key Features of Meshy 7 Text-to-3D API
-
Prompt-to-3D Generation: Create a 3D model from a written description of the desired subject, shape, style, and visual details.
-
Configurable Topology: Choose triangle or quad topology according to the intended downstream workflow.
-
Target Polygon Control: Set a target polygon count within the supported range to guide mesh density.
-
Remesh & Symmetry Options: Control whether the mesh is regenerated and how symmetry is applied.
-
Humanoid Pose Guidance: Request an A-pose or T-pose when generating a suitable humanoid subject.
-
Optional PBR & Texture Guidance: Enable PBR material generation and guide texturing with a prompt or reference image.
How to Use Meshy 7 Text-to-3D API for AI 3D Asset Creation on Flaq AI
-
Input: A required prompt between 1 and 600 characters, plus optional topology, target polygon count, remesh, symmetry, humanoid pose, PBR, texture prompt, texture image, and random seed settings.
-
Output: A generated 3D model with optional PBR material textures, returned through the Flaq AI task workflow.
-
Mesh Controls: Select triangle or quad topology, configure a target polygon count, and choose whether to remesh the generated geometry.
-
Texture Controls: Enable PBR and provide optional text or image guidance for the model's textures.
-
Capabilities: Text-to-3D generation with configurable mesh, pose, symmetry, texture, and seed controls.
Best Use Cases for Meshy 7 Text-to-3D API Integration
-
Game Asset Concepts: Generate starting models for props, environment pieces, characters, and other interactive content.
-
VR, AR & Web Experiences: Create 3D concepts that can be reviewed and prepared for spatial applications.
-
Product & Packaging Concepts: Explore three-dimensional forms before detailed modeling and production work.
-
Design Visualization: Turn short creative briefs into models for ideation, presentation, and further refinement.
-
3D Printing Preparation: Generate base geometry that can be inspected, repaired, and prepared in dedicated printing software.
Note Generated geometry should be reviewed before use in production, animation, simulation, or fabrication. Ensure prompts and reference images comply with applicable content and intellectual property policies.
Meshy 7 Text-to-3D vs Competitors: Comparative Analysis
-
Meshy 7 Text-to-3D vs. Tripo Text-to-3D
Teams comparing these models should evaluate topology options, target polygon controls, texture workflows, output requirements, and integration needs. Meshy 7 exposes these controls through the Flaq AI API. -
Meshy 7 Text-to-3D vs. Rodin Text-to-3D
The preferred option depends on the subject matter and downstream 3D workflow. Meshy 7 combines prompt-based generation with optional remeshing, pose guidance, symmetry, and PBR controls. -
Meshy 7 Text-to-3D vs. CSM
Developers can compare supported inputs, mesh controls, texturing options, and API workflow. Meshy 7 accepts a text prompt and provides configurable geometry and texture settings. -
Meshy 7 Text-to-3D vs. Luma Genie
Product teams should evaluate model behavior, available controls, output requirements, and integration format. Meshy 7 is available as a task-based API on Flaq AI. -
Meshy 7 Text-to-3D vs. Meshy 7 Image-to-3D
Text-to-3D is suited to workflows that begin with a written concept. Image-to-3D is the corresponding option when a source image should guide the generated model.