# Vimmerse Generate Text Prompt

> Vimmerse Generate Text Prompt is a paid API for AI agents from agents.vimmerse.net, paid per call via MPP, price unknown, status unknown (last checked 2026-10-31).

Generates, suggests, refines, or extracts a descriptive text prompt from images, video, or seed text for use in AI media generation workflows.

## Facts

- Endpoint: POST https://agents.vimmerse.net/v2/text/prompt?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Provider: agents.vimmerse.net
- Website: https://agents.vimmerse.net
- Canonical page: https://www.zero.xyz/c/agents-vimmerse-net-vimmerse-generate-text-prompt-38e99235
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Gv7HfM5WZ79NXKwdfn8Jp

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 agents-vimmerse-net-vimmerse-generate-text-prompt-38e99235 -d '<json body>'
```

Example prompt: Look at this product image at https://media.vimmerse.net/example/product.jpg and generate a descriptive text prompt for it using the Image2Prompt option in image mode — I want to use it for AI image generation.

## When to prefer this

Choose this endpoint when you need to programmatically generate, improve, or extract text prompts from images or video before passing them to a downstream media generation step. It is especially useful in automated pipelines where a human hasn't crafted a prompt yet, or when you want to upgrade a weak seed prompt. Prefer it over generic LLM prompting when you want vision-grounded, media-mode-aware prompt text tuned specifically for Vimmerse's image, video, scene, or audio generators.

## Known failure modes

- Missing required seed text when using RefinePrompt option — returns 422 validation error
- Invalid or inaccessible image_url or video_url — returns error or poor-quality output
- Unsupported option value — returns 422 validation error
- Timeout on large video files when extracting middle frame — returns 504 or timeout error
- Invalid mode value — returns 422 validation error

## How this service works

Generates or transforms prompt text.

| Field | Notes |
|-------|--------|
| `option` | `InspireMe` (default), `Image2Prompt`, `SuggestPrompt`, `RefinePrompt` |
| `image_url` | Primary image for vision options |
| `image2_url` | Optional second image |
| `video_url` | Uses middle frame when no `image_url` |
| `prompt` | Seed text; required for `RefinePrompt` behavior via `option` |
| `mode` | `scene`, `video`, `image`, or `audio` |

```python
import requests

r = requests.post(
    "https://api.vimmerse.net/v2/text/prompt",
    headers={"X-Api-Key": "YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "image_url": "https://media.vimmerse.net/example/product.jpg",
        "option": "Image2Prompt",
        "mode": "image",
    },
    timeout=120,
)
r.raise_for_status()
print(r.json())  # JSON string value
```

## Output

Returns a plain JSON string containing the generated, suggested, refined, or extracted text prompt ready to use as input for image, video, audio, or scene generation workflows.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "title": "GeneratePromptRequest",
 "properties": {
  "mode": {
   "type": "string",
   "title": "Mode",
   "default": "scene",
   "examples": [
    "scene",
    "video",
    "image",
    "audio"
   ],
   "description": "Refinement mode."
  },
  "option": {
   "type": "string",
   "title": "Option",
   "default": "InspireMe",
   "description": "`Image2Prompt` — describe image; `SuggestPrompt` — creative suggestion; `RefinePrompt` — improve `prompt`; `InspireMe` — auto from inputs."
  },
  "prompt": {
   "type": "string",
   "title": "Prompt",
   "default": "",
   "description": "Seed or instruction text."
  },
  "image_url": {
   "type": "string",
   "title": "Base image URL",
   "default": ""
  },
  "video_url": {
   "type": "string",
   "title": "Video URL",
   "default": "",
   "description": "Middle frame is extracted and used like an image when no image_url is set."
  },
  "image2_url": {
   "type": "string",
   "title": "Second image URL (optional)",
   "default": ""
  }
 },
 "description": "Request body for POST /v2/text/prompt."
}
```

## Response schema (JSON Schema)

```json
{
 "type": "string",
 "title": "Response Get Prompt V2 Text Prompt Post"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-vimmerse-net-vimmerse-generate-text-prompt-38e99235/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.vimmerse.net](https://www.zero.xyz/host/agents.vimmerse.net/llms.txt)