GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →

black-forest-labs/

FLUX 3 Video Extend Draft quickly continues a required input video into a draft clip with prompt-guided next-scene motion, optional synchronized audio, and flexible 5-20 second duration for rapid iteration.

video-extend
Input
Enable Safety Checker

Idle

$0.6per run·~16 / $10

ExamplesView all

Continue seamlessly as the employee and the cleaning robot race toward the end of the aisle. The robot takes a shortcut around a display while the employee quickly turns into the next aisle. A customer watches them in confusion. They reach the checkout area almost at the same time, and the employee raises his mop in playful victory while the robot slowly bumps into his shoe. The camera follows smoothly and ends on their funny standoff. Preserve the same employee, store, robot, lighting, and movement direction.

Related Models

README

FLUX 3 Draft Video Extend

FLUX 3 Draft Video Extend quickly continues a required input video into a draft extension guided by your prompt. Use it to test what should happen next, how the camera should move, and how the visual style should continue before moving to a final-quality workflow.

Why Choose This?

  • Video extension draft generation
    Continue an existing video with a prompt-guided draft extension.

  • Fast continuation testing
    Test next-scene action, visual continuity, subject behavior, camera movement, pacing, and atmosphere.

  • Prompt-guided scene development
    Describe how the video should continue after the source clip ends.

  • Optional synchronized audio
    Generate matching audio for early ambience, effects, music, or dialogue tests.

  • Flexible duration
    Choose a draft extension duration from 5 to 20 seconds.

  • Multiple aspect ratios
    Supports landscape, portrait, square, and cinematic formats.

Parameters

ParameterRequiredDescription
promptYesDescribe the next action, scene development, camera movement, mood, lighting, and visual continuity.
videoYesInput MP4 video used as the starting point. The source must be under 50 MB and under 15 seconds.
aspect_ratioNoOutput aspect ratio. Options: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.
durationNoDuration of the draft extension in seconds. Range: 5–20. Default: 5.
generate_audioNoGenerate synchronized audio for the draft extension. Default: true.

How to Use

  1. Upload the source video — Provide an MP4 video under 50 MB and under 15 seconds.
  2. Write the prompt — Describe the next event, action, camera movement, lighting, mood, and continuity direction.
  3. Choose aspect ratio — Select the output format that matches your target use case.
  4. Set duration — Choose a draft extension duration from 5 to 20 seconds.
  5. Configure audio optional — Enable generate_audio when you want to test ambience, effects, music, or dialogue.
  6. Submit — Generate the draft continuation and review the extended result.

Pricing

Pricing is based on billed extension duration.

Billed duration is rounded up to the next whole second and capped at 20 seconds. Audio generation does not add a separate charge.

Billing UnitPrice
Per 5s$0.60
Per second$0.12

Example Costs

DurationBilled DurationCost
5s5s$0.60
10s10s$1.20
15s15s$1.80
20s20s$2.40

Best Use Cases

  • Next-scene testing — Explore different continuations after an existing clip ends.
  • Alternative endings — Generate multiple draft endings from the same source video.
  • Product demo extension — Continue product motion, camera movement, or feature reveals.
  • Character action continuation — Extend character movement, gestures, reactions, or performance.
  • Advertising drafts — Test campaign ideas, transitions, and pacing from existing footage.
  • Social video concepts — Extend short clips into draft vertical, square, or widescreen content.

Pro Tips

  • Begin with the next visible action instead of repeating the entire source video.
  • State continuity requirements such as lighting, subject appearance, environment, camera movement, and mood.
  • Describe what should happen immediately after the source video ends.
  • Keep the draft prompt focused on one clear continuation event.
  • Use shorter durations for quick tests and longer durations when the continuation needs more time to develop.
  • Use a clean source video with a clear ending moment for smoother continuation.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Flux 3 Video Extend Draft API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/video-extend-draft 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 Flux 3 Video Extend Draft 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",
    "aspect_ratio": "21:9",
    "duration": 5,
    "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/video-extend-draft" \
  -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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/video-extend-draft";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "aspect_ratio": "21:9",
        "duration": 5,
        "generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  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",
    "aspect_ratio": "21:9",
    "duration": 5,
    "generate_audio": True
}

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/black-forest-labs/flux-3/video-extend-draft", 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 = 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", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Flux 3 Video Extend Draft API — Frequently asked questions

What is the Flux 3 Video Extend Draft API?

Flux 3 Video Extend Draft is a Black Forest Labs model for video extension, exposed as a REST API on WaveSpeedAI. FLUX 3 Video Extend Draft quickly continues a required input video into a draft clip with prompt-guided next-scene motion, optional synchronized audio, and flexible 5-20 second duration for rapid iteration. You can call it programmatically or try it from the playground above.

How do I call the Flux 3 Video Extend Draft 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/black-forest-labs/black-forest-labs-flux-3-video-extend-draft.

How much does Flux 3 Video Extend Draft cost per run?

Flux 3 Video Extend Draft starts at $0.6 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 Flux 3 Video Extend Draft accept?

Key inputs: `prompt`, `video`, `aspect_ratio`, `duration`, `generate_audio`. 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/black-forest-labs/black-forest-labs-flux-3-video-extend-draft.

How long does Flux 3 Video Extend Draft take to generate?

Reported generation time on WaveSpeedAI is around 83 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Flux 3 Video Extend Draft outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Black Forest Labs). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.