# Omnigen v2 text to image fal AI

Needs prompt.

Omnigen V2, served by fal.ai. $0.15 per megapixels Output is constrained to 1024x1024 and one image; reservation covers two billed megapixels, including whole-megapixel rounding. The exact receipt determines the final charge. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/omnigen-v2" and that request_id. The exact endpoint/request billing receipt is required before settlement.

- Tool ID: `fal/fal-ai-omnigen-v2`
- Name in the catalog: Omnigen V2, text to image
- Provider: [fal.ai](/providers/fal.md)
- Capability: [AI image generation](/tools/image-generation.md)
- Price: $0.3 per call
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_call",
  "amountUsd": 0.3
}
```

Pricing source: [https://fal.ai/models/fal-ai/omnigen-v2/llms.txt](https://fal.ai/models/fal-ai/omnigen-v2/llms.txt). $0.15 per megapixels Output is constrained to 1024x1024 and one image; reservation covers two billed megapixels, including whole-megapixel rounding. The exact receipt determines the final charge..

Price verification date: 2026-11-03.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "prompt": {
      "title": "Prompt",
      "type": "string",
      "description": "The prompt to generate or edit an image. Use specific language like 'Add the bird from image 1 to the desk in image 2' for better results."
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative Prompt",
      "default": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar",
      "description": "Negative prompt to guide what should not be in the image."
    },
    "cfg_range_start": {
      "type": "number",
      "maximum": 1,
      "title": "Cfg Range Start",
      "default": 0,
      "minimum": 0,
      "description": "CFG range start value."
    },
    "text_guidance_scale": {
      "type": "number",
      "maximum": 8,
      "title": "Text Guidance scale",
      "default": 5,
      "minimum": 1,
      "description": "\n            The Text Guidance scale controls how closely the model follows the text prompt.\n            Higher values make the model stick more closely to the prompt.\n        "
    },
    "image_size": {
      "type": "object",
      "properties": {
        "width": {
          "type": "integer",
          "enum": [
            1024
          ]
        },
        "height": {
          "type": "integer",
          "enum": [
            1024
          ]
        }
      },
      "required": [
        "width",
        "height"
      ],
      "additionalProperties": false,
      "default": {
        "width": 1024,
        "height": 1024
      }
    },
    "seed": {
      "title": "Seed",
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "\n            The same seed and the same prompt given to the same version of the model\n            will output the same image every time.\n        "
    },
    "output_format": {
      "type": "string",
      "title": "Output Format",
      "default": "jpeg",
      "enum": [
        "jpeg",
        "png"
      ],
      "description": "The format of the generated image."
    },
    "scheduler": {
      "type": "string",
      "title": "Scheduler",
      "default": "euler",
      "enum": [
        "euler",
        "dpmsolver"
      ],
      "description": "The scheduler to use for the diffusion process."
    },
    "enable_safety_checker": {
      "type": "boolean",
      "title": "Enable Safety Checker",
      "default": true,
      "description": "If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images."
    },
    "num_images": {
      "type": "integer",
      "maximum": 1,
      "title": "Num Images",
      "default": 1,
      "minimum": 1,
      "description": "The number of images to generate.",
      "enum": [
        1
      ]
    },
    "num_inference_steps": {
      "type": "integer",
      "maximum": 50,
      "title": "Num Inference Steps",
      "default": 50,
      "minimum": 20,
      "description": "The number of inference steps to perform.",
      "enum": [
        50
      ]
    },
    "cfg_range_end": {
      "type": "number",
      "maximum": 1,
      "title": "Cfg Range End",
      "default": 1,
      "minimum": 0,
      "description": "CFG range end value."
    },
    "image_guidance_scale": {
      "type": "number",
      "maximum": 3,
      "title": "Image Guidance scale",
      "default": 2,
      "minimum": 1,
      "description": "\n            The Image Guidance scale controls how closely the model follows the input images.\n            For image editing: 1.3-2.0, for in-context generation: 2.0-3.0\n        "
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/fal-ai-omnigen-v2",
  "input": {
    "prompt": "Make the dress blue",
    "image_size": {
      "width": 1024,
      "height": 1024
    },
    "num_images": 1,
    "num_inference_steps": 50,
    "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar",
    "cfg_range_start": 0,
    "text_guidance_scale": 5,
    "output_format": "jpeg",
    "scheduler": "euler",
    "enable_safety_checker": true,
    "cfg_range_end": 1,
    "image_guidance_scale": 2
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/omnigen-v2)

[REST inspection](https://api.agentik.cc/v1/tools/fal/fal-ai-omnigen-v2) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/fal-ai-omnigen-v2) · [Agent index](/llms.txt)