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.
निष्क्रिय
$0.2प्रति रन·~50 / $10
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.
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.
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.
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
| Duration | Cost |
|---|---|
| 5 seconds | $0.20 |
| 8 seconds | $0.32 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 2.2 I2v 480p Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-lora";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/i2v-480p-lora", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)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.
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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-i2v-480p-lora.
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.
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.
Median end-to-end generation time on WaveSpeedAI is around 65 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.