Seedream 5.0 Pro đã ra mắt | Thử trong Trình tạo ảnh →

Wan 2.2 Spicy Video Extend LoRA

wavespeed-ai /

Extend clips into unlimited longer videos with WAN 2.2 Spicy, producing smooth animation and supporting custom LoRA weights. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

lora-support
Đầu vào

Chờ

$0.2cho mỗi lần chạy·~50 / $10

Ví dụXem tất cả

Extend the video by transitioning the camera forward into the castle courtyard, revealing more towers, shifting magical energy flows, and clouds parting dramatically as the scene progresses.

Xhxs666, the girl dancing.

Extend the video by moving the camera deeper into the forest, revealing larger glowing formations, moving light orbs, and intensified magical particle flows.

Extend the video by showing the detective turning into a narrow alley, neon lights becoming dimmer, steam getting thicker, and the camera slowly closing in as tension builds.

Extend the video as drones lift off into the sky, sunlight flares intensify, multiple drones flying in formation, and the camera tracking their ascent through the clouds.

Mô hình liên quan

README

WAN 2.2 Spicy — Image-to-Video-I2V-LoRA-extend

WAN 2.2 Spicy (LoRA) is an enhanced image-to-video generation model built on the WAN 2.2 multimodal architecture, now featuring LoRA fine-tuning support. The extend version is the version optimized for generating long videos.

It transforms static images into cinematic 480p or 720p motion videos with rich color, expressive movement, and customizable style — ideal for creators, artists, and visual designers.

🔥 Why It Looks Great

  • Dynamic Realism: captures smooth, coherent motion with stable subjects and natural camera transitions.
  • Cinematic Aesthetics: reproduces professional-grade lighting, depth, and color balance.
  • Enhanced with LoRA: supports up to 3 LoRAs per job, allowing style, character, or motion customization.
  • Adaptive Motion Design: intelligently adjusts motion intensity based on prompt semantics.
  • Flexible Output: supports both portrait and landscape formats for social media or cinematic projects.

✨ Key Features

  • Expressive Motion Synthesis — vivid, coherent motion generation with stable frames.
  • LoRA Fine-Tuning (up to 3 LoRAs) — apply custom LoRAs for artistic control or stylistic consistency.
  • Flexible Duration Options — 5s or 8s video generation for short-form storytelling.
  • Artistic Style Adaptation — from realistic visuals to stylized anime or painterly looks.
  • Lighting & Color Optimization — automatic tone mapping for cinematic mood and depth.

⚙️ Specifications

  • Input: Single image (JPG, PNG)
  • Output: Video (480p / 720p, MP4 format)
  • Duration: 5s or 8s
  • LoRA Support: up to 3 LoRAs (Support high_noise and low_noise)
  • Seed Control: Optional reproducibility

💰 Pricing

ResolutionPrice per second
480p$0.04 / s
720p$0.08 / s

🧩 How to Use

  1. Upload your image (high-quality reference recommended).
  2. Enter a prompt describing motion, tone, or camera action.
  3. (Optional) Add up to 3 LoRAs under loras, high_noise_loras, or low_noise_loras.
  4. Choose resolution (480p or 720p) and duration (5s or 8s).
  5. (Optional) Set seed for reproducibility.
  6. Click Run to generate your video.

📝 Notes

  • Works best with well-lit, clear images.
  • Avoid overly complex prompts to maintain clean motion.
  • LoRA sources must be from reliable repositories with open access.
  • For stronger visual identity, test combinations of low_noise and high_noise LoRAs.
  • If the output seems static, increase motion-related phrasing in your prompt.

📄Reference

Lưu ý:Trang web này sử dụng các mô hình AI do bên thứ ba cung cấp.

Wan 2.2 Spicy Video Extend Lora API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2-spicy/video-extend-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 Spicy Video Extend Lora below.

HTTP example
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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "480p",
    "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-spicy/video-extend-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
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2-spicy/video-extend-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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "resolution": "480p",
        "duration": 5,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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));
}
Python example
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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "480p",
    "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-spicy/video-extend-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 Spicy Video Extend Lora API — Frequently asked questions

What is the Wan 2.2 Spicy Video Extend Lora API?

Wan 2.2 Spicy Video Extend Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Extend clips into unlimited longer videos with WAN 2.2 Spicy, producing smooth animation and supporting custom LoRA weights. 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 Spicy Video Extend 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 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-spicy-video-extend-lora.

How much does Wan 2.2 Spicy Video Extend Lora cost per run?

Wan 2.2 Spicy Video Extend 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 Spicy Video Extend Lora accept?

Key inputs: `prompt`, `video`, `resolution`, `duration`, `seed`, `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-spicy-video-extend-lora.

How long does Wan 2.2 Spicy Video Extend Lora take to generate?

Median end-to-end generation time on WaveSpeedAI is around 87 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Wan 2.2 Spicy Video Extend 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.

Wan 2.2 Spicy Video Extend LoRA | Custom LoRA Image API | WaveSpeedAI