Build with Hailuo 02 Standard
Make your first request
Use your Sorceress API key on your server. The playground uses your signed-in account; your application uses the same model with an API key.
curl -X POST 'https://sorceress.games/api/v1/jobs' \
-H 'Authorization: Bearer $SORCERESS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "hailuo-02-image-to-video-standard",
"input": {
"prompt": "<prompt>",
"image_url": "<image_url>",
"duration": "<duration>",
"resolution": "<resolution>"
}
}'Inputs & settings
promptstringRequiredThe text prompt describing the video to generate (Max length: 1500 characters)
durationstringRequiredRequired. Video duration in seconds: 6 or 10.
Options: 6, 10
image_urlstringRequiredThe URL of the image to use as the first frame of the video (Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
resolutionstringRequiredRequired. The resolution of the generated video.
Options: 512P, 768P
nsfw_checkerbooleanDefaults to false. When false, no additional content filtering is applied and results are returned directly by the model.
end_image_urlstringOptional URL of the image to use as the last frame of the video (Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
prompt_optimizerbooleanWhether to use the model's prompt optimizer (Boolean value (true/false))
Full input schema
{
"type": "object",
"required": [
"prompt",
"image_url",
"duration",
"resolution"
],
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"maxLength": 1500,
"description": "The text prompt describing the video to generate (Max length: 1500 characters)"
},
"duration": {
"enum": [
"6",
"10"
],
"type": "string",
"title": "Duration",
"description": "Required. Video duration in seconds: 6 or 10."
},
"image_url": {
"type": "string",
"title": "Image URL",
"format": "uri",
"x-media": "image",
"description": "The URL of the image to use as the first frame of the video (Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)"
},
"resolution": {
"enum": [
"512P",
"768P"
],
"type": "string",
"title": "Resolution",
"description": "Required. The resolution of the generated video."
},
"nsfw_checker": {
"type": "boolean",
"title": "NSFW checker",
"description": "Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model."
},
"end_image_url": {
"type": "string",
"title": "End image URL",
"format": "uri",
"x-media": "image",
"description": "Optional URL of the image to use as the last frame of the video (Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)"
},
"prompt_optimizer": {
"type": "boolean",
"title": "Prompt optimizer",
"description": "Whether to use the model's prompt optimizer (Boolean value (true/false))"
}
}
}Results, saved runs & billing
Media requests return a job ID. Poll GET /api/v1/jobs/:id until it succeeds or fails; keep the same ID while it is processing. Long chat requests can also return a saved job to poll. Completed outputs are stored in your account, and successful work is billed using your model's current rates.
A multi-step workflow may include separately billed successful actions. If a connection drops, check your saved run before submitting it again.
