Image-to-video API

Example request

curl -X POST https://videogenapi.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kling-3","prompt":"The product rotates slowly under studio light","image_url":"https://example.com/product.jpg","duration":5}'

Models with image-to-video

Need first/last frame or multi-image? Veo 3.1 accepts reference_image_urls. Details in generate docs.

How image-to-video works

Image-to-video uses your image as the first frame and generates the motion described in your prompt. The request is the same as text-to-video with one extra field, so you can add it to an existing integration in minutes.

Which model for which image?

Side-by-side specs and measured generation times: Kling 3 vs MiniMax H3, Kling 3 vs Veo 3.1, all comparisons.

Writing a good motion prompt

• Describe the motion, not the image. The model already sees the picture. Say what moves: "the camera slowly orbits the bottle", "she turns her head and smiles".
• Name one camera move. Dolly in, pan left, slow orbit or static shot. Several moves in one clip tend to fight each other.
• Keep the subject consistent. Avoid asking for new objects or people that are not in the image; the first frame anchors the result.
• Match the aspect ratio. Use a vertical image for 9:16 social video and a landscape image for 16:9.

Python and JavaScript

import os, time, requests

API = "https://videogenapi.com/api/v1"
H = {"Authorization": f"Bearer {os.environ['VIDEOGEN_API_KEY']}"}

job = requests.post(f"{API}/generate", headers=H, json={
    "model": "kling-3",
    "prompt": "The camera slowly orbits the sneaker, soft studio light",
    "image_url": "https://example.com/sneaker.jpg",
    "duration": 5,
}).json()

while True:
    s = requests.get(f"{API}/status/{job['generation_id']}", headers=H).json()
    if s["status"] in ("completed", "failed"):
        break
    time.sleep(5)
print(s.get("video_url"))

const API = "https://videogenapi.com/api/v1";
const headers = { Authorization: `Bearer ${process.env.VIDEOGEN_API_KEY}`, "Content-Type": "application/json" };

const job = await (await fetch(`${API}/generate`, { method: "POST", headers, body: JSON.stringify({
  model: "minimax-h3",
  prompt: "Waves roll onto the beach, foam catching the light",
  image_url: "https://example.com/beach.jpg",
  duration: 6,
}) })).json();

let s;
do {
  await new Promise(r => setTimeout(r, 5000));
  s = await (await fetch(`${API}/status/${job.generation_id}`, { headers })).json();
} while (!["completed", "failed"].includes(s.status));
console.log(s.video_url);

More in the Python and JavaScript guides.

Image-to-video API FAQ