Struct InferenceCreateAsyncInvokeBodyInput

Source

pub struct InferenceCreateAsyncInvokeBodyInput {
    pub enable_safety_checker: Option<bool>,
    pub guidance_scale: Option<f64>,
    pub num_images: Option<NonZeroU64>,
    pub num_inference_steps: Option<NonZeroU64>,
    pub output_format: Option<String>,
    pub prompt: Option<String>,
    pub seconds_total: Option<NonZeroU64>,
    pub text: Option<String>,
}

Expand description

The input parameters for the model invocation. Fields vary by model type.

For image generation models (e.g., fal-ai/flux/schnell, fal-ai/fast-sdxl), use prompt along with optional image parameters like output_format, num_inference_steps, guidance_scale, num_images, and enable_safety_checker.

For audio generation models (e.g., fal-ai/stable-audio-25/text-to-audio), use prompt along with seconds_total to control the duration.

For text-to-speech models (e.g., fal-ai/elevenlabs/tts/multilingual-v2), use text with the content you want converted to speech.

JSON schema

{
 "description": "The input parameters for the model invocation. Fields vary by model type.\n\nFor **image generation** models (e.g., `fal-ai/flux/schnell`, `fal-ai/fast-sdxl`), use `prompt` along with optional image parameters like `output_format`, `num_inference_steps`, `guidance_scale`, `num_images`, and `enable_safety_checker`.\n\nFor **audio generation** models (e.g., `fal-ai/stable-audio-25/text-to-audio`), use `prompt` along with `seconds_total` to control the duration.\n\nFor **text-to-speech** models (e.g., `fal-ai/elevenlabs/tts/multilingual-v2`), use `text` with the content you want converted to speech.\n",
 "type": "object",
 "properties": {
   "enable_safety_checker": {
     "description": "Whether to enable the safety checker for generated content.",
     "examples": [
       true
     ],
     "type": [
       "boolean",
       "null"
     ]
   },
   "guidance_scale": {
     "description": "Controls how closely the image generation model follows the prompt. Higher values produce output more closely matching the prompt.\n",
     "examples": [
       3.5
     ],
     "type": [
       "number",
       "null"
     ]
   },
   "num_images": {
     "description": "The number of images to generate.",
     "examples": [
       1
     ],
     "type": [
       "integer",
       "null"
     ],
     "minimum": 1.0
   },
   "num_inference_steps": {
     "description": "The number of inference steps to use during image generation. More steps generally produce higher quality output but take longer.\n",
     "examples": [
       4
     ],
     "type": [
       "integer",
       "null"
     ],
     "minimum": 1.0
   },
   "output_format": {
     "description": "The desired output format or aspect ratio for image generation.\n",
     "examples": [
       "landscape_4_3"
     ],
     "type": [
       "string",
       "null"
     ]
   },
   "prompt": {
     "description": "The text prompt describing the desired output. Used for image generation and audio generation models.\n",
     "examples": [
       "A futuristic city at sunset"
     ],
     "type": "string"
   },
   "seconds_total": {
     "description": "The total duration in seconds for generated audio. Used for audio generation models.\n",
     "examples": [
       60
     ],
     "type": [
       "integer",
       "null"
     ],
     "minimum": 1.0
   },
   "text": {
     "description": "The text content to convert to speech. Used for text-to-speech models.\n",
     "examples": [
       "This text-to-speech example uses DigitalOcean multilingual voice."
     ],
     "type": "string"
   }
 },
 "additionalProperties": true
}