50% zniżki na modele Vidu Q3 i Q3 Pro · Tylko w WaveSpeedAI | 20 maja – 2 czerwca

Hunyuan Video 1.5 Image to Video

wavespeed-ai /

HunyuanVideo-1.5 (i2v) is a lightweight 8.3B parameter image-to-video model that generates high-quality videos from images with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Wejście

Przeciągnij i upuść lub kliknij, aby przesłać

preview

Bezczynny

$0.1za uruchomienie·~10 / $1

Dalej:

PrzykładyZobacz wszystkie

A cinematic anime-style image-to-video sequence. Start from this frame: a high-school girl with long dark hair stands in the rain at night, holding a clear umbrella in a neon-lit Japanese backstreet, her uniform shirt slightly wet, looking back with a faintly sad expression. Continue the story at normal speed, no slow motion: the camera slowly tracks forward toward her as raindrops tap on the umbrella and colorful signs reflect on the wet pavement. Her phone vibrates in her pocket, she glances down to read a short message, her eyes soften with mixed relief and disappointment. She looks once more down the empty street as if hoping to see someone arrive, then takes a quiet breath, tightens her grip on the umbrella, and starts walking toward the brighter end of the alley, passing steaming food stalls and blurred pedestrians under umbrellas. Neon reflections ripple around her footsteps, city sounds grow louder, anime aesthetic, detailed rain effects, gentle handheld-style motion, melancholic yet hopeful mood.

A cinematic noir-style image-to-video shot. Start from the given frame: a middle-aged detective in a beige trench coat and fedora stands in the rain on a 1940s city street under the glowing “BLUE MOON TAVERN” neon sign, holding a slightly crumpled black-and-white photograph. Continue the story: light rain falls on the wet cobblestones, car headlights pass slowly behind him, reflections shimmer on the street. The camera moves forward at a natural pace, no slow motion, as he studies the photo, turns it over to reveal a handwritten message, then frowns. The tavern sign flickers, a distant car door slams, and a shadowy figure briefly appears in the tavern doorway before disappearing inside. The detective pockets the photograph, looks up with quiet determination, and walks toward the tavern entrance through the rain. Realistic lighting, detailed textures, classic film-noir atmosphere, normal speed, cinematic framing.

A cinematic cyberpunk image-to-video sequence. Start from this frame: a lone armored figure with a glowing visor walks down the center of a neon-soaked street at night, skyscrapers and holographic billboards towering on both sides, rain falling and reflecting the colors on the wet asphalt. Continue the story at normal speed (no slow motion): the camera tracks backward as the figure keeps walking with steady, confident steps, drones and flying cars crossing the sky above, their lights sweeping past. A message flashes briefly across one of the giant screens with a warning about a citywide lockdown; the character glances up, the visor UI flickers, then they receive a holographic mission briefing projected from the helmet. Police sirens echo in the distance, a car screeches to a stop behind them, and a drone turns its camera toward the character, scanning. The figure clenches their fists, the visor shifts to a combat color, and they stride forward toward the end of the street, disappearing into a haze of neon fog. High detail, rich reflections, dynamic city atmosphere, smooth camera motion, real-time pacing.

A romantic vintage-style image-to-video sequence. Start from this frame: a couple in classic coats stand close together on a wet cobblestone street at dusk, sharing a single umbrella, laughing and looking into each other’s eyes, warm streetlamps glowing behind them and a small cinema sign in the background. The camera gently tracks around them at normal speed (no slow motion) as raindrops fall and reflections shimmer on the stones. They calm their laughter, he brushes a raindrop from her hair, she playfully nudges his shoulder, then they decide to walk. Still under the umbrella, they turn and stroll down the street toward the distant lights, occasionally bumping shoulders and exchanging soft smiles, passing the “Cinéma du Cœur” entrance as its marquee flickers on. The city feels quiet and intimate, warm golden light, soft bokeh, natural real-time motion, cozy romantic mood.

Image-to-video horror sequence. Start from this exact frame: an old, decaying house labeled “ST. JUDE’S ORPHANAGE – EST. 1888,” shattered windows, overgrown yard, and a long-haired figure in a torn white gown standing motionless at the top of the steps. A single distant flash of lightning briefly lights the sky, then fades, leaving only the dim, overcast gloom. The camera makes a very slow, steady push toward the porch at normal speed (no slow motion), as light rain begins to fall and the old wood creaks quietly. Keep the figure almost completely still, with only tiny natural motions: her dress and hair moving slightly in the wind, and the faint rise and fall of breathing. Once, a weak glow appears behind an upstairs window, suggesting vague child-shaped shadows before it goes dark again. As the camera reaches the bottom of the steps, the orphanage sign swings gently with a soft squeak, and the figure’s head slowly lifts a few degrees toward the camera in one continuous, smooth movement. No jump cuts, no teleporting, just subtle, realistic motion, gritty cinematic look, heavy atmosphere, detailed rain and shadows, unsettling supernatural mood, real-time pacing.

Powiązane modele

README

HunyuanVideo-1.5 Image-to-Video

HunyuanVideo-1.5 is Tencent’s lightweight, state-of-the-art video generation model. The image-to-video variant on WaveSpeedAI lets you animate a single still image into a smooth, cinematic clip guided by your text prompt, while keeping the original visual style and character identity stable.

Key features

  • High-quality image-to-video generation with strong motion coherence
  • Lightweight 8.3B-parameter design for fast inference
  • Multiple resolutions: 480p, 720p
  • Video durations: 5 s, 8 s, and 10 s

Limits and performance

  • Input: single image (any reasonable resolution; automatically resized/preprocessed)
  • Output: short video clip at selected resolution, duration, and aspect ratio
  • Recommended duration: up to 10 seconds per clip
  • Best performance with clear, well-lit images and a prompt that specifies motion, camera behavior, and mood

Pricing

ResolutionPrice per second
480p$0.02 / s
720p$0.04 / s

How to use

  1. Upload your input image (this becomes the starting frame of the video).
  2. Enter a prompt describing the motion, camera movement, environment changes, and overall mood.
  3. Choose the resolution: 480p, 720p.
  4. Select the aspect ratio (16:9 for landscape or 9:16 for vertical/mobile).
  5. Choose the duration: 5, 8, or 10 seconds.
  6. Optionally set the seed for reproducibility.
  7. Run the job and wait for processing.
  8. Preview the generated video and download it from the WaveSpeedAI dashboard.

Tips for best results

  • Use a clean, high-resolution input image; avoid heavy compression and motion blur.
  • In the prompt, specify both what moves (hair, clothes, camera, background elements) and what stays stable (character pose, framing).
  • Mention camera behavior explicitly (e.g., “slow push-in,” “handheld shake,” “static camera with subtle parallax”).
  • Shorter durations (5–8 s) tend to produce the most coherent motion for complex scenes.
  • For a series of related clips, reuse the same seed and similar prompts to keep style and identity consistent.

Notes

HunyuanVideo-1.5 I2V is ideal for creators who want fast, controllable animation from still images without heavyweight hardware. It can be combined with high-end image models on WaveSpeedAI (such as Nano Banana Pro or Seedream v4) for a full pipeline: generate a keyframe with an image model, then bring it to life with HunyuanVideo.

Dostępność:Ta strona korzysta z modeli AI udostępnianych przez podmioty trzecie.

Hunyuan Video 1.5 Image To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-video-1.5/image-to-video 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 Hunyuan Video 1.5 Image To Video below.

HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-video-1.5/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "image": "https://example.com/your-input.jpg",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "720p",
    "duration": 5,
    "seed": -1
}'

# 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/hunyuan-video-1.5/image-to-video", {
        "image": "https://example.com/your-input.jpg",
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "resolution": "720p",
        "duration": 5,
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output
Python example
# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/hunyuan-video-1.5/image-to-video",
    {
    "image": "https://example.com/your-input.jpg",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "720p",
    "duration": 5,
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Hunyuan Video 1.5 Image To Video API — Frequently asked questions

What is the Hunyuan Video 1.5 Image To Video API?

Hunyuan Video 1.5 Image To Video is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. HunyuanVideo-1.5 (i2v) is a lightweight 8.3B parameter image-to-video model that generates high-quality videos from images with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. 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 Hunyuan Video 1.5 Image To Video 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/hunyuan-video-1.5-image-to-video.

How much does Hunyuan Video 1.5 Image To Video cost per run?

Hunyuan Video 1.5 Image To Video starts at $0.10 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 Hunyuan Video 1.5 Image To Video accept?

Key inputs: `prompt`, `image`, `resolution`, `duration`, `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/hunyuan-video-1.5-image-to-video.

How long does Hunyuan Video 1.5 Image To Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 79 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Hunyuan Video 1.5 Image To Video 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.