WAN 2.2 A14B Image-to-Video model generates unlimited 480p videos from images and supports custom LoRAs for personalized styles and fine-tuning. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.2per run·~50 / $10
ExamplesView all
The video opens with a cat. As the video progresses, the cat begins to deflate it, gradually shrinking and losing shape, eventually flattening completely into a lifeless, deflated mass on the ground
Point-of-view from inside a parked car during a rainy night. Streetlights and neon signs blur through raindrops on the windshield. Occasional cars pass by, water streaks down the glass. Reflections dance. Intimate, moody, photorealistic, low-light atmosphere.
A golden retriever runs through a grassy field in slow motion. The camera follows at low angle. Sunlight catches in the fur. Blades of grass bend underfoot. Happy expression, high-speed footage feel, lifelike animation, shallow focus on the subject.
An elderly man sits in a wooden chair reading a book by a window. Outside, trees sway gently. Dust particles float in the warm sunlight. Camera slowly pushes in. Peaceful and intimate, photorealistic detail, natural aging, documentary-style stillness.
Wide-angle shot of the ocean as dark clouds gather and lightning flashes in the distance. Waves crash with increasing intensity. Wind stirs the camera slightly. Cinematic real-world lighting, highly detailed skies, immersive weather dynamics.
A woman jogs through a city park in the early morning. Birds scatter, leaves rustle. Camera tracks behind her steadily. Warm sunrise colors, mist in the air, subtle lens flare. Sportswear realism, urban naturalism, subtle wind movement.
A construction worker welds steel beams on a building site. Sparks fly. The camera captures fine particles in the air. High-contrast lighting, authentic gear and tools, real-time hand movement. Industrial realism, blue-collar atmosphere
A young woman stands alone on a city rooftop at dusk, wind gently blowing through her hair. Neon lights begin to glow in the distance. She leans on the railing, gazing at the skyline. Camera slowly circles around her. Cinematic lighting, reflective mood, photorealistic skin and fabric.
A painter sits near a large window, dabbing oil paints onto a canvas. Sunlight streams in, casting long shadows. Paint tubes and brushes are scattered on the table. The artist adjusts their palette and wipes their hands on an apron. Hands-in-focus, lifelike textures, realism with creative atmosphere.
A female dancer in a futuristic bodysuit performs sharp, popping dance moves inside a dark room lit by pulsating neon strips. The camera orbits around her in slow circular motion, dynamic lighting syncs with her movements, colorful motion trails follow each arm wave, small particles float midair, creating a surreal, rhythm-driven atmosphere.
Related Models
README
Wan-2.2-i2v-480p-lora
Wan 2.2 is a multimodal generative video model built with an MoE (Mixture of Experts) architecture, combining high-noise and low-noise experts. This design allows the model to adapt denoising steps and generate cinematic-quality video with fine motion control, complex scene handling, and faithful semantic alignment.
With LoRA support (up to 3 LoRAs per job), Wan 2.2 becomes even more customizable, enabling creators to apply fine-tuned artistic or stylistic layers to their video generations.
Key Features
-
Cinematic-level Aesthetic Control: Professional camera language, multi-dimensional control over lighting, color, and composition.
-
Large-scale Complex Motion: Smoothly restores natural motion, supports multi-subject dynamics, and enhances controllability.
-
Precise Semantic Compliance: Excels at complex scene understanding and multi-object generation, ensuring faithful creative intent.
-
LoRA Integration: Import up to 3 LoRAs per job for both high-noise and low-noise experts, with adjustable blending scale.
Limits and Performance
-
Resolution: 480p
-
Duration options: 5s or 8s
-
Input types:
-
Prompt
-
Image (First Frame)
-
Last Image (Last Frame)
-
LoRAs: up to 3 high-noise LoRAs + 3 low-noise LoRAs or just 3 LoRAs
-
Seed: reproducibility control
Pricing
| Duration | Cost |
|---|---|
| 5 seconds | $0.20 |
| 8 seconds | $0.32 |
How to Use
- Upload an initial image.
- Write a prompt describing the video scene.
- (Optional) Add a last_image for smooth transitions.
- Select duration (5s or 8s).
- Add LoRAs (up to 3 for high-noise experts, 3 for low-noise experts).
- (Optional) Set a seed for reproducibility.
- Run the job and preview/download your video.
Pro Tips
- Use image + last_image for storyboarding transitions.
- Apply high-noise LoRAs for global style changes, and low-noise LoRAs for subtle refinements.
- Keep LoRA scale values balanced (0.5–1.0 recommended) for natural blending.
- Choose 5s for quick iterations and 8s for polished results.
Note
- If you did not upload the image locally, please ensure that the image URL is accessible! A successfully accessible image will display a preview in the interface.
Reference
Wan 2.2 I2v 480p Lora API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-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 480p Lora below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-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",
"negative_prompt": "blurry, low quality, distorted",
"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/wan-2.2/i2v-480p-lora", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"negative_prompt": "blurry, low quality, distorted",
"duration": 5,
"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-480p-lora",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"negative_prompt": "blurry, low quality, distorted",
"duration": 5,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 I2v 480p Lora API — Frequently asked questions
What is the Wan 2.2 I2v 480p Lora API?
Wan 2.2 I2v 480p Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. WAN 2.2 A14B Image-to-Video model generates unlimited 480p videos from images and supports custom LoRAs for personalized styles and fine-tuning. 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 480p 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-480p-lora.
How much does Wan 2.2 I2v 480p Lora cost per run?
Wan 2.2 I2v 480p Lora 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 Wan 2.2 I2v 480p Lora accept?
Key inputs: `prompt`, `image`, `duration`, `seed`, `negative_prompt`, `high_noise_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-480p-lora.
How long does Wan 2.2 I2v 480p Lora take to generate?
Average end-to-end generation time on WaveSpeedAI is around 67 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 480p 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.