Image-to-video from a product photo

A product photo is a reference, not a guarantee that every detail stays identical in later frames. For a mug, bottle or package, assess product fidelity before judging the camera movement. Use input material that you are entitled to use.

Prepare the shot

• Prepare a photo with clear edges and room around the product.
• Compose the first frame for the final aspect ratio instead of relying on automatic expansion.
• Upload it as the first frame in Studio and inspect the file preview.
• Describe the change: a slow push-in, moving light or gentle steam. Do not describe a different product.
• Check the logo, closure, reflections and proportions at the start, middle and end.
• Add advertising copy and audio after visual approval, and retain the source photo.

Review before publication

• The logo keeps its letters.
• The shot does not reveal an invented hidden side.
• The first frame matches the target aspect ratio.

API input example

The JSON below is the request body for POST /v1/generate. Use your own accessible image URL where a reference is required.

{
  "model": "kling-3.0",
  "input": {
    "prompt": "A slow camera push toward the product, preserve its silhouette, soft studio lighting, no new objects, no text",
    "duration": 5,
    "image_url": "https://example.com/product.jpg"
  }
}

Model and cost

Use Kling 3.0. Its current unit price is from $0.169 per second. Check the pricing page and calculator for your settings. Credits never expire, there is no subscription and failed generations are free. A successful output is billable even if you choose not to publish it.

FAQ

Can a prompt replace a product reference photo?

It cannot establish the exact appearance of your item. Use an image input and inspect the result frame by frame.

Can I check the request before a paid run?

Yes. Check the model schema and the cost shown in Studio. Local demo API tests validate request handling but do not prove the visual or audio quality of the real model.

Where are the supported parameters?

Model details and the generation API guide list the supported inputs. Preview mode does not provide a real generated result.