Trabajo
UCloud ModelVerse Image Generation API Integration Guide
Technical guide and API specification for invoking UCloud ModelVerse text-to-image endpoints, parameters, and async polling.
Usar este prompt
# UCloud ModelVerse Text-to-Image API Integration Guide
## Endpoint Overview
- **Base URL:** `https://api.umodelverse.ai`
- **Method:** `POST`
- **Auth Header:** `Authorization: Bearer <YOUR_API_KEY>`
- **Content-Type:** `application/json`
---
## 1. Text-to-Image Generation Request
```bash
curl -X POST "https://api.umodelverse.ai/v1/images/generations" \
-H "Authorization: Bearer $MODELVERSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-schnell",
"prompt": "clean professional RF engineering illustration, microstrip patch antenna cross-section diagram, annotated, neutral white background",
"size": "1024x1024",
"n": 1,
"response_format": "url"
}'
```
### Parameter Reference
- `model`: Supported models include `flux-schnell`, `flux-dev`, `sdxl-turbo`, `dall-e-3`.
- `prompt`: Detailed descriptive prompt (English recommended for highest quality).
- `size`: Aspect ratio/resolution (e.g. `1024x1024`, `1536x864`, `864x1536`).
- `n`: Number of images to generate (default `1`).
- `response_format`: `url` (hosted image URL) or `b64_json` (Base64 string).
---
## 2. Handling Async Tasks (If Applicable)
For asynchronous models, check task status using:
```bash
curl -X GET "https://api.umodelverse.ai/v1/tasks/{task_id}" \
-H "Authorization: Bearer $MODELVERSE_API_KEY"
```
Response status:
- `PENDING`: Task queued.
- `RUNNING`: Image currently rendering.
- `SUCCESS`: Complete, array of image URLs returned in `result`.
- `FAILED`: Error details returned in `error` object.
Todavía no hay comentarios. Añade la primera nota útil.