Diskon 50% model Vidu Q3 & Q3 Pro · Hanya di WaveSpeedAI | 20 Mei – 2 Jun

Wan 2.1 I2V Plus 720P

alibaba /

WAN 2.1 i2v-plus 720P turns still images into smooth image-to-video clips, enabling unlimited AI videos from image inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Input

Seret & lepas atau klik untuk mengunggah

preview
If set to true, the prompt optimizer will be enabled.

Siap

$0.7per run·~14 / $10

Selanjutnya:

ContohLihat semua

A beautiful woman sitting by a cafe window, her expression subtly shifts from thoughtful to a gentle, knowing smile. Sunlight streams through the window, creating soft lens flares that move across the frame. The steam from her coffee cup slowly rises. Cinematic, soft focus, 4K.

Dolly Zoom A young detective finds a crucial clue in a cluttered archive room. He stands up, a look of shock and realization dawning on his face. The camera performs a dolly zoom on him: the camera physically moves backward while the lens zooms in. This keeps him the same size in the frame but compresses and distorts the background, dramatically amplifying his internal shock and sense of destiny.

A man standing on the edge of a rooftop at sunset. His coat and hair gently sway in the wind. The city lights in the background begin to twinkle and blur into bokeh. The camera slowly pushes in on his silhouette. Moody and atmospheric.

A young girl holding a dandelion. She gently blows on it, and the seeds disperse into the air, glistening in the afternoon sun. A gentle breeze rustles the leaves on the trees behind her. The camera follows a single seed floating away. Nostalgic and heartwarming.

A woman holds a clear umbrella in a rain-soaked city at night. Raindrops slide down the umbrella's surface and splash on the neon-lit pavement. Reflections of the city lights shimmer and distort on the wet ground. Her gaze slowly lifts to meet the camera. Cinematic, moody, 8K, hyper-realistic.

A man in a trench coat walks alone on a wet city street after the rain, reflections of neon lights shimmer in the puddles at his feet. His expression is thoughtful and melancholic, with the blurred city nightscape behind him. 4K quality, photorealistic style.

In a serene forest, a female hiker has paused, gently extending her hand towards a butterfly that has landed on her gloved fingers. Sunlight filters through the dense canopy, creating dappled light and visible beams (crepuscular rays) that illuminate the side of her focused, gentle face. The camera is very steady with almost no movement, emphasizing the tranquility, harmony, and the delicate connection between human and nature in this moment. Shot with a shallow depth of field to isolate the subject.

An elderly grandfather sits on an old sofa by a fireplace, telling stories of the past to his grandson. The warm glow of the fire illuminates their faces; the grandfather's is full of kind wrinkles and a nostalgic glint in his eyes, while the grandson listens, captivated, his expression a mix of curiosity and admiration. The room is dimly lit, filled with a sense of warmth, comfort, and generational connection. Shot with a 35mm cinema lens to create a soft, vintage texture.

A historian in a vast, sunlit library archive, surrounded by towering shelves of old books and manuscripts. She is carefully examining an ancient, fragile map with a magnifying glass, her expression one of intense concentration and awe. Dust motes dance in the shafts of light streaming from the high arched windows. The camera executes a slow, subtle zoom-in on her face, capturing the moment of discovery. The atmosphere is one of reverence, silence, and the weight of history.

Starting from a still image of snowy mountains, the video shows the first light of sunrise spreading across the peaks. Thin mist moves slowly in the valley, and the clouds shift gently in the sky, giving a sense of calm winter beauty.

Model Terkait

README

WAN 2.1 — Image-to-Video Model-Plus (720p)

WAN 2.1 is an advanced image-to-video generation model that transforms static images into smooth, cinematic 5-second motion clips. This 720p version provides the ideal balance between visual quality and generation speed — perfect for professional content creation and rapid storytelling.

🌟 Key Features

  • Cinematic Motion Generation Adds natural depth, parallax, and camera motion effects to bring still images to life.

  • High Temporal Consistency Maintains stable structure and lighting across all frames for smooth playback.

  • Balanced 720p Output Delivers clear HD video optimized for both web and mobile distribution.

  • Lightweight and Efficient Produces professional-quality motion in seconds, minimizing compute cost and latency.

  • Creative Flexibility Works across diverse visual styles — from portraits and landscapes to products and illustrations.

⚙️ Capabilities

  • Input: Single image (JPEG / PNG)
  • Output: 5-second 720p MP4 video
  • Supports: Camera motion, lighting drift, and subject parallax effects

💰 Pricing

DurationResolutionCost (USD)
5 seconds720p$0.70

💡 Best Use Cases

  • Social Media & Marketing — Animate photos into attention-grabbing motion content.
  • E-commerce & Branding — Add cinematic motion to product visuals and hero shots.
  • Art & Photography — Turn static compositions into immersive short clips.
  • Education & Storytelling — Visualize concepts and narratives dynamically.

📝 Notes

  • For best results, upload clear, high-resolution images with good lighting and contrast.
  • Simple prompts and compositions yield the most stable motion.
Aksesibilitas:Situs web ini menggunakan model AI yang disediakan oleh pihak ketiga.

Wan 2.1 I2v Plus 720p API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.1/i2v-plus-720p 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 Wan 2.1 I2v Plus 720p below.

HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.1/i2v-plus-720p" \
  -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,
    "enable_prompt_expansion": false,
    "negative_prompt": "blurry, low quality, distorted",
    "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("alibaba/wan-2.1/i2v-plus-720p", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "duration": 5,
        "enable_prompt_expansion": false,
        "negative_prompt": "blurry, low quality, distorted",
        "seed": -1
});

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

output = wavespeed.run(
    "alibaba/wan-2.1/i2v-plus-720p",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "duration": 5,
    "enable_prompt_expansion": false,
    "negative_prompt": "blurry, low quality, distorted",
    "seed": -1
}
)

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

Wan 2.1 I2v Plus 720p API — Frequently asked questions

What is the Wan 2.1 I2v Plus 720p API?

Wan 2.1 I2v Plus 720p is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.1 i2v-plus 720P turns still images into smooth image-to-video clips, enabling unlimited AI videos from image inputs. 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 Wan 2.1 I2v Plus 720p 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/alibaba/alibaba-wan-2.1-i2v-plus-720p.

How much does Wan 2.1 I2v Plus 720p cost per run?

Wan 2.1 I2v Plus 720p starts at $0.70 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 Wan 2.1 I2v Plus 720p accept?

Key inputs: `prompt`, `image`, `duration`, `seed`, `negative_prompt`, `enable_prompt_expansion`. 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/alibaba/alibaba-wan-2.1-i2v-plus-720p.

How long does Wan 2.1 I2v Plus 720p take to generate?

Average end-to-end generation time on WaveSpeedAI is around 345 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Wan 2.1 I2v Plus 720p outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.