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

Wan FLF2V

wavespeed-ai /

Wan-2.1 FLF2V converts a start and end frame into a smooth, coherent video sequence, bridging frames with realistic motion transitions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Đầu vào

Chờ

$0.3cho mỗi lần chạy·~33 / $10

Tiếp theo:

Ví dụXem tất cả

glass flower blossom

Small birds fly freely in the sky.

Mô hình liên quan

README

Wan FLF2V — wavespeed-ai/wan-flf2v

Wan FLF2V is a first-last-frame-to-video model that generates a short video by interpolating a coherent motion path between a first_image and a last_image, guided by an optional text prompt. Provide the starting frame and the ending frame, then describe what happens in between (e.g., a transformation, assembly, reveal, or scene change). The model produces a smooth transition clip while keeping the beginning and ending states aligned with your provided frames.

Key capabilities

  • First-last-frame guided video generation (first_image → last_image)
  • Prompt-guided in-between action and transformation logic
  • Supports negative_prompt to reduce artifacts and unwanted motion
  • Size selection for different output resolutions
  • Seed control for reproducible results

Use cases

  • Transformation sequences (frame → completed object, sketch → final render)
  • Product assembly and reveal animations (parts → finished product)
  • Before/after transitions (makeover, restoration, environment change)
  • Visual storytelling between two keyframes for ads and social
  • Storyboard “in-betweening” from a first and last shot

Pricing

ModeSize tier5s10s
StandardNon-720p size$0.30$0.45
FastNon-720p size$0.15$0.225
Standard720p size (1280×720 / 720×1280)$0.40$0.60
Fast720p size (1280×720 / 720×1280)$0.25$0.375

Inputs

  • first_image (required): starting frame
  • last_image (required): ending frame
  • prompt (optional): describe the transition and what happens in between
  • negative_prompt (optional): what to avoid (blur, jitter, distortion, artifacts)

Parameters

  • duration: video length in seconds
  • size: output resolution selection (e.g., 832×480)
  • num_inference_steps: sampling steps
  • guidance_scale: prompt adherence strength
  • seed: random seed (-1 for random; fixed value for reproducible results)

Prompting guide (FLF2V)

A good prompt explains how the first becomes the last:

Template: Fixed camera. Start exactly from the first image and end exactly at the last image. In between, show [mechanism] smoothly and coherently. No flicker, no warping.

Example prompts

  • Transform the car frame into a complete vehicle. Parts assemble step-by-step, bolts tighten, panels slide into place, paint and reflections appear gradually, cinematic lighting, smooth motion, fixed camera.
  • A rough clay sculpture becomes a polished ceramic statue, cracks heal, glaze forms, subtle dust motes, steady camera, seamless transition.
  • A bare room becomes fully furnished, objects slide into place naturally, lighting stays consistent, no jitter.
Lưu ý:Trang web này sử dụng các mô hình AI do bên thứ ba cung cấp.

Wan Flf2v API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-flf2v 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 Flf2v below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "first_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "size": "832*480",
    "num_inference_steps": 30,
    "guidance_scale": 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-flf2v" \
  -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-flf2v";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "first_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "duration": 5,
        "size": "832*480",
        "num_inference_steps": 30,
        "guidance_scale": 5,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "first_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "size": "832*480",
    "num_inference_steps": 30,
    "guidance_scale": 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-flf2v", 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 Flf2v API — Frequently asked questions

What is the Wan Flf2v API?

Wan Flf2v is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. Wan-2.1 FLF2V converts a start and end frame into a smooth, coherent video sequence, bridging frames with realistic motion transitions. 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 Flf2v 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-flf2v.

How much does Wan Flf2v cost per run?

Wan Flf2v starts at $0.30 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 Flf2v accept?

Key inputs: `prompt`, `duration`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. 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-flf2v.

How long does Wan Flf2v take to generate?

Median end-to-end generation time on WaveSpeedAI is around 198 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 Flf2v 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 FLF2V | Fast Image-to-Video API | WaveSpeedAI