# Generate images from text prompts

Robot: `/image/generate`

🤖/image/generate generates images from text prompts using AI.

Stage: ga

## Usage example

Inpaint an image by uploading an original image and a mask image, then use both files in /image/generate:

```json
{
  "steps": {
    ":original": {
      "robot": "/upload/handle"
    },
    "inpainted": {
      "robot": "/image/generate",
      "use": [
        {
          "name": ":original",
          "as": "image"
        },
        {
          "name": ":original",
          "as": "mask"
        }
      ],
      "model": "google/nano-banana-pro",
      "prompt": "Replace the masked area with a breaching whale. Keep the rest of the image unchanged.",
      "format": "png"
    }
  }
}
```

## Parameters

* `interpolate`: Controls whether Assembly Variables are interpolated for individual instruction fields.

  By default, most Robot instruction fields interpolate Assembly Variables. Set this to `false` to treat every instruction field as literal text, or set an individual field path to `false` to treat only that field as literal text. For Robot-specific fields that are literal by default, set this to `true` or set that field path to `true` to opt back into interpolation.

  Use field names such as `path`, or dotted paths such as `ffmpeg.vf` for nested objects.

* `output_meta`: Allows you to specify a set of metadata that is more expensive on CPU power to calculate, and thus is disabled by default to keep your Assemblies processing fast.

  For images, you can add `"has_transparency": true` in this object to extract if the image contains transparent parts and `"dominant_colors": true` to extract an array of hexadecimal color codes from the image.

  For images, you can also add `"blurhash": true` to extract a [BlurHash](https://blurha.sh) string — a compact representation of a placeholder for the image, useful for showing a blurred preview while the full image loads.

  For videos, you can add the `"colorspace": true` parameter to extract the colorspace of the output video.

  For videos, you can also add `"interlaced": true` to detect whether the video is interlaced. This combines the cheap ffprobe `field_order` flag with a bounded `idet` sampling pass over the first frames of the source, exposing `interlaced`, `field_order`, and a diagnostic `interlace_detection` object under `file.meta`. This is computationally expensive and billed accordingly.

  For audio, you can add `"mean_volume": true` to get a single value representing the mean average volume of the audio file.

  You can also set this to `false` to skip metadata extraction and speed up transcoding.

* `user_meta`: Adds custom metadata to each file emitted by this Robot without modifying the file’s contents.

  The values are merged with any existing `user_meta` carried by the input file. If both objects contain the same key, this Robot’s value takes precedence. Assembly Variables are supported, for example `{ "internal_file_id": "${file.id}" }`.

* `result`

* `queue`: Setting the queue to 'batch', manually downgrades the priority of jobs for this step to avoid consuming Priority job slots for jobs that don't need zero queue waiting times

* `force_accept`: Force a Robot to accept a file type it would have ignored.

  By default, Robots ignore files they are not familiar with.
  [🤖/video/encode](/docs/robots/video-encode.md), for
  example, will happily ignore input images.

  With the `force_accept` parameter set to `true`, you can force Robots to accept all files thrown at them.
  This will typically lead to errors and should only be used for debugging or combatting edge cases.

* `ignore_errors`: Ignore errors during specific phases of processing.

  Setting this to `["meta"]` will cause the Robot to ignore errors during metadata extraction.

  Setting this to `["execute"]` will cause the Robot to ignore errors during the main execution phase.

  Setting this to `true` is equivalent to `["meta", "execute"]` and will ignore errors in both phases.

* `use`: Specifies which Step(s) to use as input.

  For inpainting, provide both the source image and mask through `use`, typically with:

  ```json
  {
    "use": [
      { "name": ":original", "as": "image" },
      { "name": ":original", "as": "mask" }
    ]
  }
  ```

  Best practice:

  * Tag source and mask inputs explicitly using `as` (or semantic upload field names)
  * Keep the prompt focused on what should change in the masked/transparent region
  * Leave the model/provider choice to the robot defaults unless you have a specific need

* `model`: The AI model to use. Defaults to `google/nano-banana`. Supported models include `flux-1.1-pro-ultra`, `flux-schnell`, `recraft-v3`, `google/nano-banana`, `google/nano-banana-2`, `google/nano-banana-pro`, `openai/gpt-image-2`, and `stability-ai/stable-diffusion-inpainting`. The legacy alias `gpt-image-2` is also accepted for backwards compatibility.

* `prompt`: Prompt describing the desired image. For inpainting, describe what should appear in the masked/transparent region and that the rest should stay unchanged.

* `format`: Output format. Defaults depend on model: png for Google models and openai/gpt-image-2, svg for recraft-v3, jpeg for others. Google models currently return PNG only.

* `seed`: Seed for the random number generator.

* `aspect_ratio`: Requested output aspect ratio. For Google models, width/height can also be used and orientation is derived automatically when aspect\_ratio is omitted.

* `height`: Requested output height in pixels (mainly used by Google image models and openai/gpt-image-2).

* `width`: Requested output width in pixels (mainly used by Google image models and openai/gpt-image-2).

* `style`: Style of the generated image.

* `num_outputs`: Number of output variants to generate (1-10).

* `provider`: Chooses the best provider based on your request.