Wan 2.2 T2V 5B is a 720P text-to-video model that generates unlimited AI videos from simple text prompts, producing consistent high-quality 720p outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.05per run·~20 / $1
ExamplesView all
An old man adjusts his glasses while reading a newspaper in the sunlit park
A woman in business attire waits at a crosswalk as cars pass by, her hair gently blown by wind
A girl leans out of a cabin window, watching the snow fall quietly onto the forest outside
A chef sprinkles chopped parsley over a sizzling pan of food, steam rising gently
A woman quietly exhales and closes her eyes while listening to calming music through headphones
A child pets a golden retriever that’s lying calmly on the living room floor
A young woman stands alone on a foggy train platform at dawn, eyes filled with quiet determination. The camera slowly dolly-zooms in as a train approaches, steam billowing in golden light. Her coat flutters gently in the wind, and there's a subtle trembling in her lip — she's about to leave everything behind. High cinematic contrast, muted colors, shallow depth of field.
An old man sits on a porch at sunset, softly smiling as he watches kids play in the distance. The camera glides past blooming flowers and lands on his weathered face, capturing tears pooling in his eyes. Every wrinkle tells a story. Golden-hour lighting, handheld camera sway, soft film grain texture.
A teenage boy runs breathlessly through a rainy alley, lit only by flickering neon signs. The camera tracks him in a close side-follow, droplets hitting the lens. His eyes are wide with panic and guilt. Slow-motion as he turns a corner and stops, panting, soaked and crying. Dark cinematic tones, Blade Runner aesthetic.
A soldier stares at a photograph of his family inside a muddy trench, expression torn between longing and despair. The camera pushes in slowly through smoke and chaos, framing him in stark chiaroscuro. He closes his eyes and inhales deeply, steadying himself. Desaturated war-drama palette, ambient battlefield tension.
A lone astronaut drifts in space, Earth in the distance. Inside the helmet, we see her face — eyes tired but filled with awe. The camera orbits around her slowly, revealing the vast silence around. Subtle lens warping, soft breathing audible, Interstellar-style cinematic depth.
A child clutches a broken toy, watching their parents argue behind a glass door. The camera sits at child’s eye-level, slowly pushing forward as the argument escalates in muffled silence. The child’s eyes well with tears but remain locked on the toy. Moody lighting, domestic realism, A24-style tone.
Horse galloping across an open grassland, mane flowing in the wind, dirt kicked up from hooves, camera moving sideways at matching speed, long shadows cast on the field, gentle hills in the distance, motion blur and lens vibration on every step
Professional skier descending a steep snowy slope, carving sharp turns, snow powder bursting with each move, camera following behind with steady shake, dramatic mountain backdrop, light glare from snow surface, cinematic depth and movement trails
Related Models
README
Wan 2.2 Text-to-Video 5B 720p
Wan 2.2 Text-to-Video 5B 720p is a powerful text-to-video generation model built on a 5 billion parameter architecture. Generate high-quality 720p HD videos from text descriptions at an incredibly affordable price — perfect for content creators, marketers, and creative projects.
Why It Stands Out
- 5B parameter model: Large-scale architecture for superior video quality and prompt understanding.
- HD 720p output: Generate crisp 1280×720 videos with rich detail and visual clarity.
- Ultra-affordable: High-quality video generation at just $0.05 per video.
- Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
- Smooth motion: Advanced temporal modeling ensures natural, fluid movement.
- Reproducibility: Use the seed parameter to recreate exact results or explore variations.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| size | No | Output resolution (default: 1280×720). |
| seed | No | Set for reproducibility; -1 for random. |
How to Use
- Write a prompt describing the scene, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
- Select size — choose the resolution that fits your needs.
- Set a seed (optional) for reproducible results.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Social Media Content — Create engaging video clips for TikTok, Reels, and Shorts.
- Marketing & Advertising — Produce concept videos and promotional content affordably.
- Storytelling & Animation — Generate scenes for short films and creative projects.
- Rapid Prototyping — Test video concepts quickly before committing to higher budgets.
- Creative Exploration — Experiment with different prompts and styles at minimal cost.
Pricing
| Output | Price |
|---|---|
| Per video | $0.05 |
Pro Tips for Best Quality
- Be detailed in your prompt — describe subject, action, environment, lighting, and mood.
- Include style keywords like "cinematic," "realistic," "anime," or "documentary" to guide the aesthetic.
- Describe camera movements like "slow pan," "tracking shot," or "static wide angle."
- Keep prompts focused — overly complex descriptions may dilute the output quality.
- Fix the seed when iterating to compare different prompt adjustments.
Notes
- Processing time varies based on current queue load.
- Please ensure your prompts comply with content guidelines.
Wan 2.2 T2v 5b 720p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-5b-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 2.2 T2v 5b 720p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-5b-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",
"size": "1280*720",
"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/wan-2.2/t2v-5b-720p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/wan-2.2/t2v-5b-720p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 T2v 5b 720p API — Frequently asked questions
What is the Wan 2.2 T2v 5b 720p API?
Wan 2.2 T2v 5b 720p is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. Wan 2.2 T2V 5B is a 720P text-to-video model that generates unlimited AI videos from simple text prompts, producing consistent high-quality 720p outputs. 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 2.2 T2v 5b 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/wavespeed-ai/wan-2.2-t2v-5b-720p.
How much does Wan 2.2 T2v 5b 720p cost per run?
Wan 2.2 T2v 5b 720p 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.
What inputs does Wan 2.2 T2v 5b 720p accept?
Key inputs: `prompt`, `size`, `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/wan-2.2-t2v-5b-720p.
How long does Wan 2.2 T2v 5b 720p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 90 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 2.2 T2v 5b 720p 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.