SkyReels V1 is an open-source, human-centric video foundation model fine-tuned from HunyuanVideo on ~10M high-quality film and TV clips to deliver realistic human motion and scene synthesis. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
En attente
$0.2par exécution·~50 / $10
ExemplesTout voir
The Amazon rainforest at dawn, sunlight piercing through the dense canopy, creating mottled spots of light. A colorful hummingbird hovers in front of a blooming orchid, its wings vibrating at high speed, almost invisible. Macro lens, capturing the fine texture of the hummingbird's feathers and the dewdrops on the petals. High-speed photography, extreme detail, vivid colors.
soldiers after the end of a war looking at the destruction as the flames expand. Zoom out
Two eccentric clowns in orange striped suits dancing joyfully in a lively marketplace. Colorful stalls in the background, playful atmosphere, exaggerated expressions, dynamic body movement, festive and surreal vibe, background stay still
the Elf is dancing in the forest
Close-up of a confident anime boy with spiky black hair and sharp blue eyes, wearing a torn scarf and a battle-worn jacket, smirking, cel-shaded coloring, early 2000s shonen anime style, bold line art, intense gaze, dramatic lighting on the face
A lone astronaut floats above Earth, sunlight reflecting on their visor, complete silence except for breathing
A robotic arm assembling electronic parts on a conveyor belt, precise movements, industrial lighting, sparks flying
An elderly craftsman is carefully polishing a wooden sculpture with his calloused hands. Close-up shot focusing on his concentrated eyes and the wrinkles on his face. In the workshop, afternoon sunlight streams through a dusty window, creating beams of light, with fine wood dust floating in the air. Cinematic, 4K, ultra-detailed, natural lighting.
FPV cockpit view, hands grip the controls as the ship dives through laser fire and exploding debris. Enemy fighters streak past the glass, HUD elements flash red. Distant explosions light up the void.Intense, fast-paced, immersive sci-fi action
An elderly couple on a park bench, sharing a pair of earphones, their heads leaning against each other with eyes closed, listening quietly to music. Autumn leaves surround them, and the afterglow of the sunset dyes their silver hair golden. Photo taken with a 50mm prime lens, capturing this quiet and profound moment, warm color palette, emotionally charged.
A sprawling metropolis cityscape after a downpour, wet asphalt streets reflecting vibrant neon signs from skyscrapers. A lone tram moves steadily through the frame. The camera pans slowly from a low angle, capturing the glistening reflections on the ground. Cinematic, photorealistic, 4K, moody lighting.
An underwater tracking shot gliding smoothly through a vibrant coral reef. Schools of small, brightly colored tropical fish swim past the camera. Sunlight filters down through the turquoise water, creating dancing light patterns on the seafloor. Documentary style, vivid colors, serene atmosphere.
A magical, slow-motion tracking shot through a dense summer forest at twilight. Thousands of fireflies begin to glow, their gentle pulses of light creating a mesmerizing, twinkling galaxy among the ancient trees. The camera glides effortlessly along a mossy path, capturing the ethereal dance of light. The air is filled with a soft, warm, golden-green luminescence. Dreamlike, serene, enchanting, cinematic depth of field.
A vibrant, joyful shot of a diverse group of friends laughing and chatting at a rooftop garden party. Sunlight filters through the leaves of lush plants and flowers, creating dappled light on their smiling faces. One person is strumming a ukulele. The camera circles the group slowly, capturing candid interactions and the stunning city skyline in the background. Warm lighting, joyful, candid moments, positive vibes, shallow depth of field.
Modèles associés
README
SkyReels V1 — wavespeed-ai/SkyReels-V1
SkyReels V1 is an image-to-video model that animates a single reference image into a short, cinematic clip guided by a text prompt. Upload an image to anchor the subject and composition, then describe the motion, camera language, atmosphere, and visual style you want. The model is well-suited for nature shots, cinematic macro moments, and smooth “living photo” style animations, with seed control for reproducible variations.
Key capabilities
- Image-to-video generation anchored to a reference image
- Prompt-driven motion, atmosphere, and camera intent
- Works well for cinematic “living photo” animation and natural motion
- Seed control for reproducible outputs
Use cases
- Animate nature photography (birds, insects, plants, weather, light rays)
- Cinematic macro shots (wings fluttering, pollen drifting, dew shimmering)
- Turning a still image into a short b-roll clip for edits and trailers
- Rapid iteration: generate multiple takes by changing prompt or seed
- Stylized scene animation with consistent composition
Pricing
| Output | Price per run |
|---|---|
| Image-to-Video (per generation) | $0.20 |
Inputs
- prompt (required): what happens in the video (action + scene + camera)
- image (required): reference image (subject/composition anchor)
Parameters
- prompt: describe subject, motion, environment, camera, and style
- image: input image (upload or URL)
- seed: random seed (-1 for random; fixed value for reproducible results)
Prompting guide (I2V)
For stronger results, write prompts like a director’s brief:
- Subject: who/what is on screen
- Action: what moves over time (flutter, drift, sway, shimmer)
- Scene: where it happens + time/lighting
- Camera: macro close-up, slow push-in, gentle pan (optional)
- Constraints: keep composition consistent with the reference image
Example prompts
- Amazon rainforest at dawn, sun rays piercing the canopy, a hummingbird hovering by an orchid, wings vibrating rapidly, macro lens, shallow depth of field, drifting pollen and dust motes, slow cinematic push-in, natural motion.
- A close-up of a flower with dew drops sparkling, gentle breeze moving petals, soft morning light, subtle camera pan, realistic motion, cinematic b-roll.
SkyReels V1 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/SkyReels-V1 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 SkyReels V1 below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/SkyReels-V1" \
-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",
"seed": 0
}'
# 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/SkyReels-V1", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"seed": 0
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/SkyReels-V1",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"seed": 0
}
)
print(output["outputs"][0]) # → URL of the generated outputSkyReels V1 API — Frequently asked questions
What is the SkyReels V1 API?
SkyReels V1 is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. SkyReels V1 is an open-source, human-centric video foundation model fine-tuned from HunyuanVideo on ~10M high-quality film and TV clips to deliver realistic human motion and scene synthesis. 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 SkyReels V1 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/SkyReels-V1.
How much does SkyReels V1 cost per run?
SkyReels V1 starts at $0.20 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 SkyReels V1 accept?
Key inputs: `prompt`, `image`, `seed`. 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/SkyReels-V1.
How long does SkyReels V1 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 35 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use SkyReels V1 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.