Wan 2.2 T2V 5B is a 5B text-to-video model with LoRA support that generates 720p videos from text prompts for easy personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Boşta
$0.1çalıştırma başına·~10 / $1
An elderly man sitting at a wooden desk in a sunlit study, dust particles dancing in the air, the camera slowly dollies in from the window, passing through curtains, then tilts down to reveal the man's wrinkled hands flipping through an old photo album, warm afternoon lighting casting long shadows
A fashion model walking confidently down a rooftop runway at golden hour, the skyline of a modern city behind her, wind blowing through her hair and dress, drone-style overhead shot circles her slowly, then cuts to a low-angle shot tracking her walk, dramatic lens flare from the setting sun
A firefighter emerging from thick smoke, backlit by orange flames and flashing red lights, slow-motion tracking shot from the ground level upward, revealing a face covered in ash and sweat, camera rotates slightly to follow the movement as they rescue a child from the rubble
A barista in a cozy café pouring latte art into a ceramic cup, soft morning sunlight streaming through the window blinds, coffee steam rising in the air, bookshelves in the background
First-person POV of someone riding a bicycle through a forest trail at golden hour, sunlight flickering through the trees, dappled light patterns on the dirt path, hands gripping handlebars visible, subtle vibrations from rough terrain, birds flying overhead, distant sound of a river, immersive and realistic motion, soft wind sounds, ultra-realistic texture detail on leaves and ground
A lone traveler in a long coat standing on a cliffside at dawn, facing the vast ocean, wind flapping their coat, seagulls soaring past, camera slowly circles around the back of the character, ocean waves crashing below, sky turning from blue to gold, moody atmosphere
Rain-soaked window overlooking a city skyline, droplets slowly sliding down the glass, distant thunderstorm with flickering lightning, camera remains static but reflections change subtly over time, moody and immersive
A young woman in a red windbreaker running down a narrow alleyway at night, neon signs reflecting on wet pavement, camera tightly follows her from the front like a selfie stick, slight shake, realistic facial expressions, shallow depth of field, dramatic lighting, rain drizzling softly, cinematic street ambience, bokeh lights in the background, energetic atmosphere, realistic motion blur
A young man running on a beach at sunrise, camera tracking smoothly beside him, sand kicking up under his feet, waves rolling beside him, seagulls flying in slow motion, glowing sun rising on the horizon, joyful energy, natural lighting with motion blur
A hiker with a large backpack crossing a wooden bridge in a forest, camera follows from behind and gradually rises to reveal a waterfall in the distance, birds flying overhead, water below sparkling, wind rustling through leaves, immersive outdoor environment
Wan 2.2 T2V 5B is a 5B-parameter text-to-video model with LoRA support that generates 5-second, 1280×720 videos from text prompts. It is built on WAN AI’s Mixture of Experts (MoE) architecture, combining high-noise and low-noise experts across denoising timesteps for sharp details, smooth motion, and strong cinematic style.
.safetensors URL.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-5b-720p-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 T2v 5b 720p Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-5b-720p-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/t2v-5b-720p-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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"size": "1280*720",
"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/t2v-5b-720p-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 T2v 5b 720p Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Wan 2.2 T2V 5B is a 5B text-to-video model with LoRA support that generates 720p videos from text prompts for easy personalization. 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-t2v-5b-720p-lora.
Wan 2.2 T2v 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.
Key inputs: `prompt`, `size`, `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-t2v-5b-720p-lora.
Median end-to-end generation time on WaveSpeedAI is around 83 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.