RunwayML Gen4 Turbo is an image-to-video model that generates high-quality videos from images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Boşta
$0.05çalıştırma başına·~20 / $1
A model wears a sculptural, avant-garde gown made from recycled plastics and metals. She stands in a minimalist concrete space, holding an unconventional, dynamic pose. The lighting is harsh and sharp, creating strong geometric shadows on her and the garment. A high-contrast black and white photograph, full of artistic flair and high-fashion impact.
Early morning in a bustling Singaporean wet market, a vendor is spraying fresh vegetables with water to keep them crisp. Water droplets glisten on the green leaves, with customers browsing for ingredients in the background. Light filters through gaps in the market's ceiling, and the air is filled with a sense of dampness and freshness. Documentary photography style, capturing the vibrant essence of market life.
At dusk, the silhouettes of cranes at a Singaporean construction site are set against a brilliant sunset. Several construction workers wearing hard hats are packing up their tools, getting ready to leave. The image is filled with an industrial and powerful feeling, yet also a sense of tranquility after a day's labor. High contrast, focusing on light, shadow, and silhouettes.
In a well-lit, modern office, a diverse team (various ethnicities, ages) is brainstorming around a desk. A woman is writing ideas on a whiteboard while others engage in a focused discussion. The photo style is bright and professional, emphasizing teamwork and a positive work environment.
On a sunny weekend, a family is having a picnic by the sea at East Coast Park. They have food spread out on a checkered picnic blanket, and the children are flying a kite nearby. In the background is the calm sea with container ships in the distance. The image has vibrant colors and is filled with a sense of family happiness and a relaxed holiday atmosphere.
A hiker, carrying a backpack, is walking on the TreeTop Walk suspension bridge at MacRitchie Reservoir's nature trail. He has paused to look out over the vast green rainforest and the tranquil reservoir below. Shot with a wide-angle lens, showcasing the magnificence of nature and the harmonious coexistence between humans and the environment.
Inside a modern library at the National University of Singapore (NUS), several students are gathered around a large table for a group discussion. Sunlight streams through massive floor-to-ceiling windows, illuminating them and their open books. In the background are tall bookshelves and other students studying intently. The scene is bright and quiet, full of academic atmosphere and youthful energy.
On a hot afternoon, several people of different ages and ethnicities are waiting quietly on a bench at a bus stop. The intense sun casts a sharp shadow of the bus stop's roof onto the ground. An "Auntie" is fanning herself, while a student next to her looks down at his phone. The air seems to shimmer with heat, the image capturing the lazy and sweltering feel of a Singaporean afternoon.
A young woman, wearing noise-canceling headphones, sits alone in the corner of a retro cafe in Tiong Bahru. The light from her laptop screen illuminates her focused face. Afternoon sun filters through the blinds, casting dappled light and shadows on her and the wooden table. Photorealistic style, shallow depth of field, with the focus on the profile of her face, creating a quiet and concentrated work atmosphere.
At Maxwell Food Centre, an elderly chicken rice stall owner leans against his stall for a short breather after the lunch rush. He's wearing a slightly faded Polo shirt, with beads of sweat still on his forehead, his eyes showing a hint of fatigue mixed with satisfaction. Documentary photography style, high-contrast black and white, capturing a genuine moment of a laborer.
At sunrise, a woman in a sports tank top is jogging along the coastline of East Coast Park. Her hair, damp with sweat, flies in the air as she runs. The rising sun has colored the sky orange, leaving a golden path of light on the sea's surface. Captured with a high-speed shutter, the photo is full of a healthy, energetic vibe.
Bring your images to life with AI-powered video generation. Runway Gen4 Turbo transforms static images into dynamic videos based on your text descriptions — perfect for creating cinematic motion, animated scenes, and engaging visual content.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the motion and action you want (e.g., "The model walks forward, fabric flowing in the wind"). |
| image | Yes | Source image to animate (upload or public URL). |
| aspect_ratio | No | Output aspect ratio: 16:9, 4:3, 1:1, 3:4, or 9:16. Leave empty to match source. |
Flat rate per video generation.
| Output | Cost |
|---|---|
| Per second | $0.01 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/runwayml/gen4-turbo with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Gen4 Turbo below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/runwayml/gen4-turbo" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 5,
"aspect_ratio": "16:9"
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("runwayml/gen4-turbo", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 5,
"aspect_ratio": "16:9"
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"runwayml/gen4-turbo",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 5,
"aspect_ratio": "16:9"
}
)
print(output["outputs"][0]) # → URL of the generated outputGen4 Turbo is a Runwayml model for video generation from images, exposed as a REST API on WaveSpeedAI. RunwayML Gen4 Turbo is an image-to-video model that generates high-quality videos from images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-gen4-turbo.
Gen4 Turbo starts at $0.050 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `aspect_ratio`, `duration`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-gen4-turbo.
Average end-to-end generation time on WaveSpeedAI is around 36 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Runwayml). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.