Lynx by converts images into subject-consistent videos, preserving visual consistency across frames for seamless animations and reliable subject fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.5per run·~20 / $10
ExamplesView all
A thrilling snowboarding descent down a snowy mountain slope, powder snow exploding in all directions. The camera follows in a chase-drone perspective, weaving between pine trees, catching lens flares from the bright sun.
A hummingbird hovers among flowers, its wings beating at an incredibly high frequency, almost a blur. High-speed photography captures this moment in slow motion, showing the detail of each wing flap as it extends its long beak to sip nectar.
In a smoky, 1920s-style speakeasy, a woman in a flapper dress is energetically dancing the Charleston, her steps fast and vibrant. The camera circles her, capturing the swing of her fringe skirt and the engaged expressions of the band members, with a grainy, old-film look.
A group of friends sits around a campfire at night. The fire crackles and sparks fly. One person is playing the guitar while others hum along softly, looking at each other with genuine smiles. The camera slowly pans between their warm-lit faces, capturing the flickering firelight and sincere emotions.
A girl in a red dress joyfully running through a golden wheat field, her hair flying in the wind, a brilliant smile on her face. The camera slowly tracks her movement, capturing the moment sunlight streams across her face, cinematic, slow motion.
An old man on a park bench slowly looks up at the sky. A flock of pigeons suddenly takes flight from beside him, soaring past the camera. His expression shifts from calm to surprise, then to a gentle smile. Close-up shot focusing on the wrinkles and emotional changes on his face.
Two medieval knights in full plate armor are dueling in a castle courtyard. Their swords clash violently, creating sparks. A slow-motion shot captures the moment the blades connect and the dazzling glare of sunlight reflecting off their helmets.
A painter is working on a large canvas. The shot starts with a close-up of the artist's focused eyes, then switches to a macro shot of the brush, showing the paint being powerfully applied and blended on the canvas. As the camera pulls back, a vibrant abstract painting is gradually revealed.
The man slowly lifts the barbell up to his shoulders.
Time-lapse of a majestic mountain range from dawn to dusk. Clouds surge and flow like rivers between the peaks, the sun's shadow rapidly sweeps across the valleys, and finally, stars create brilliant trails across the night sky.
Related Models
README
Lynx
Easily create subject-consistent videos with Lynx, an advanced image-to-video model designed to keep a stable visual appearance across frames. Whether you're making dynamic animations or smooth video content, Lynx ensures your subject stays consistent, delivering professional-quality results effortlessly.
Why it looks great
- Subject consistency: preserves the identity, appearance, and details of the subject across all frames.
- Smooth motion: generates fluid, natural-looking animations without jitter.
- Flexible aspect ratios: supports 16:9, 9:16, and 1:1 for versatile use cases.
- Prompt control: guide motion, style, and atmosphere with descriptive text.
- Image-driven video: start from any uploaded image and transform it into a short video clip.
Limits and Performance
- Output resolution: depends on chosen aspect ratio (16:9, 9:16, or 1:1).
- Max clip length per job: 5 seconds
- Processing speed: ~5–12 seconds of wall time per 1 second of video (varies by queue and complexity)
Pricing
Each run costs just $0.5!!!
Billing Rules
- Flat rate: $0.50 per generation
- Each run produces a 5-second clip
How to Use
- Write a prompt to describe the motion, scene, or style.
- Upload an image as the subject reference (JPG or PNG).
- Choose the aspect_ratio: 16:9, 9:16, or 1:1.
- Submit the job.
- Download your generated 5-second video.
Pro tips for best quality
- Use high-resolution, clear source images for stronger subject consistency.
- Be specific in your prompts (e.g., “walking forward in a forest with cinematic lighting”).
- Choose the aspect ratio according to your target platform (e.g., 9:16 for TikTok, 16:9 for YouTube).
Lynx API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/lynx 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 Lynx below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/lynx" \
-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",
"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].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/lynx", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"aspect_ratio": "16:9"
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/lynx",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"aspect_ratio": "16:9"
}
)
print(output["outputs"][0]) # → URL of the generated outputLynx API — Frequently asked questions
What is the Lynx API?
Lynx is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. Lynx by converts images into subject-consistent videos, preserving visual consistency across frames for seamless animations and reliable subject fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Lynx API?
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/wavespeed-ai/lynx.
How much does Lynx cost per run?
Lynx starts at $0.50 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.
What inputs does Lynx accept?
Key inputs: `prompt`, `image`, `aspect_ratio`. 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/wavespeed-ai/lynx.
How long does Lynx take to generate?
Average end-to-end generation time on WaveSpeedAI is around 92 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Lynx outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.