# Vimmerse Text-to-Image Generation

> Vimmerse Text-to-Image Generation is a paid API for AI agents from agents.vimmerse.co, paid per call via x402, $0.12/call, status unknown (last checked 2026-11-04, last successful call 2026-11-03).

Generates 1–4 images from a text prompt using a selectable AI model (or auto-selected model), returning output image URLs in the response asset.

## Facts

- Endpoint: POST https://agents.vimmerse.co/v2/image/text-2-image?utm_source=zero.xyz
- Price: $0.12/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-04
- Last successful call: 2026-11-03
- Success rate: 25% of calls made through Zero
- Activations on Zero: 4
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vimmerse-text-to-image-generation-de63c3d1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3S_vb-H4e4vgjDCTDmYQx

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability vimmerse-text-to-image-generation-de63c3d1 -d '<json body>'
```

Example prompt: Generate 2 images of a futuristic city skyline at sunset with neon reflections on wet streets, using the FluxPro model, in 16:9 aspect ratio, and apply super-resolution enhancement.

## When to prefer this

Choose this endpoint when you need to generate still images from text descriptions with fine-grained control over model selection (including premium options like FluxPro, GPTImage, or Stable Diffusion 3.5), quantity (up to 4 images per call), and aspect ratio. It is especially useful when you want auto-model selection (AutoI), optional super-resolution enhancement, or asynchronous generation with webhook callbacks. Prefer this over video generation endpoints when the output should be static images, not video clips.

## Known failure modes

- Invalid or empty prompt returns a 400 error
- Unsupported aspect ratio or model enum value causes a validation error
- Exceeding quantity maximum of 4 returns a validation error
- Insufficient credits for the selected model tier causes a payment or authorization error
- Webhook URL unreachable results in failed delivery with no retry guarantee
- Async job may remain in 'processing' state if upstream model is overloaded

## How this service works

Generates one to four images from a text prompt with the chosen model, and returns the asset with the output URLs in results. AutoI picks a model automatically. Credits depend on the model tier and the quantity.

## Output

Returns an asset object containing the generation status and a results array with output image URLs. If async_mode is true, returns immediately with status 'processing' and an asset_id that can be polled via GET /v2/asset/{asset_id}; if false, waits and returns the completed images directly.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "option": {
   "enum": [
    "AutoI",
    "Seedream",
    "NanoBananaT2",
    "NanoBananaPro",
    "QwenImage",
    "GPTImage",
    "FluxPro",
    "FluxTurbo",
    "NanoBanana",
    "FluxKontextPro",
    "StableDiffusion3.5"
   ],
   "type": "string",
   "default": "AutoI",
   "description": "Model: AutoI picks one automatically. The choice sets the credits per call; POST /v2/image/estimate-credits returns the exact number for this body."
  },
  "prompt": {
   "type": "string",
   "description": "Text description of the image to generate."
  },
  "quantity": {
   "type": "integer",
   "default": 1,
   "maximum": 4,
   "minimum": 1,
   "description": "Number of images, 1 to 4."
  },
  "async_mode": {
   "type": "boolean",
   "default": false,
   "description": "When true the call returns at once with status processing and the asset id, and GET /v2/asset/{asset_id} returns the result when status is success. When false (default) the call waits for the images."
  },
  "webhook_url": {
   "type": "string",
   "format": "uri",
   "description": "Optional callback URL that receives the finished asset."
  },
  "aspect_ratio": {
   "enum": [
    "21:9",
    "16:9",
    "4:3",
    "3:2",
    "1:1",
    "2:3",
    "3:4",
    "9:16",
    "9:21"
   ],
   "type": "string",
   "default": "16:9",
   "description": "Output aspect ratio."
  },
  "enhance_image": {
   "type": "boolean",
   "default": false,
   "description": "Applies 1x super-resolution after generation."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vimmerse-text-to-image-generation-de63c3d1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.vimmerse.co](https://www.zero.xyz/host/agents.vimmerse.co/llms.txt)