Wan 2.2 i2v-5B-720p is a 5B image-to-video model producing 720p videos with LoRA support for style customization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.1per run·~10 / $1
ExamplesView all
Vintage film stock look, simulating footage from a handheld 16mm camera during WWII. A soldier in a European battlefield trench cautiously peeks over the edge of his helmet. Rainwater trickles down the muddy trench walls, and smoke hangs in the air. A muffled explosion is heard in the distance, causing a slight camera shake. Desaturated color tone, strong grain, with minor scratches and jitters on the film to create the realism of a historical documentary.
A golden retriever puppy running along a beach shoreline, waves crashing nearby, camera follows in a low tracking shot, sand flying, tongue out, joyful expression, slow motion and speed ramp effects, vivid natural lighting
POV shot of a cyclist riding through a bustling city street at night, neon lights reflecting on wet asphalt, cars passing by, camera slightly shaking for realism, motion blur on sides, fast-paced energy, cinematic look
A Formula 1 car speeding down a track, low-angle tracking shot, motion blur on wheels and background, wind turbulence, sparks as it scrapes the ground, zoom past the camera with Doppler sound effect implied, heat haze from engine
A glowing jellyfish slowly pulsing and drifting through deep blue water, bioluminescent trails, camera follows its fluid motion, tiny bubbles floating up, rays of light piercing the darkness, surreal underwater dream
A skier descending a snowy mountain slope at high speed, camera tracks from behind, snow spraying from skis, motion blur on trees, GoPro-style perspective, sun glare on snow, adrenaline and action-focused
An ocean cliffside during a storm, waves crashing violently against rocks, sea spray rising high, dark clouds swirling overhead, camera flies past the cliff’s edge, high realism, intense motion
A person sitting under a tree in a golden wheat field, wind rustling through the tall stalks, sunlight shimmering through branches above, camera circling around from behind, distant birds flying in formation, peaceful late summer atmosphere
A farmer leading a donkey cart down a dusty rural road at sunset, camera slowly panning from behind, sun low on the horizon casting long shadows, dust particles in the air, trees swaying gently in the distance, earthy and cinematic
A figure jogging through a tunnel at dawn, seen from behind, warm light at the end of the tunnel casting long shadows, camera tracking behind with slight handheld motion, dust particles floating, breath misting in the cold air
Related Models
README
Wan 2.2 i2v-5b-720p-lora
Wan 2.2 5B is a new-generation multimodal video model built by WAN AI. It uses an MoE (Mixture of Experts) architecture with high-noise and low-noise experts allocated across denoising timesteps, enabling sharper detail, cleaner motion, and richer cinematic style in short video clips.
Why it looks great
- Cinematic-level aesthetic control Aligned with professional film-making standards, with fine control over lighting, color palette, composition, camera lens and movement.
- Large-scale complex motion Handles dramatic actions, crowd scenes, character interactions, and challenging camera paths with smooth, stable motion.
- Precise semantic compliance Strong scene understanding and multi-object generation, producing shots that stay close to the creative brief.
- 5B parameter scale The 5-billion-parameter backbone brings higher fidelity textures, more consistent character details, and better temporal coherence.
Pricing
- Just $0.1 per run!
How to Use
- In the prompt box, describe the scene, characters, motion, camera, lighting, and style.
- (Optional) Add up to 3 LoRA adapters in the LoRA section.
- Set the seed (−1 for random, or a fixed number for reproducible runs).
- Click Run and wait for the video to render, then preview and download.
For detailed LoRA tutorials:
Wan 2.2 I2v 5b 720p Lora API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-5b-720p-lora 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 I2v 5b 720p Lora below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-5b-720p-lora" \
-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": -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/i2v-5b-720p-lora", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"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/i2v-5b-720p-lora",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 I2v 5b 720p Lora API — Frequently asked questions
What is the Wan 2.2 I2v 5b 720p Lora API?
Wan 2.2 I2v 5b 720p Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Wan 2.2 i2v-5B-720p is a 5B image-to-video model producing 720p videos with LoRA support for style customization. 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 I2v 5b 720p Lora 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-i2v-5b-720p-lora.
How much does Wan 2.2 I2v 5b 720p Lora cost per run?
Wan 2.2 I2v 5b 720p Lora 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 Wan 2.2 I2v 5b 720p Lora accept?
Key inputs: `prompt`, `image`, `seed`, `loras`. 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-i2v-5b-720p-lora.
How long does Wan 2.2 I2v 5b 720p Lora take to generate?
Average end-to-end generation time on WaveSpeedAI is around 91 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 I2v 5b 720p Lora 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.