FLUX 3 Start-End-to-Video Draft quickly generates a transition between required start and end images, with prompt-guided motion, optional synchronized audio, and flexible 5-20 second duration for rapid keyframe iteration.
Idle
$0.3per run·~33 / $10
He carefully adds buildings, trees and streetlights piece by piece. The camera shows his hands and smooth overhead views of the growing town. Tiny lights gradually turn on across the miniature streets, and the final shot pulls back as a small train begins moving around the completed model. He also grows from a kid to a man.
FLUX 3 Draft Start-End-to-Video quickly generates a transition between a required starting image and a required ending image. Use it to test action, transformation, camera movement, pacing, and visual style between two keyframes before moving to a final-quality workflow.
Start-and-end-frame control
Generate a video transition from a defined first frame to a defined final frame.
Fast transition preview
Quickly test movement, transformation, camera paths, environment changes, and pacing.
Prompt-guided motion
Describe how the subject, scene, lighting, and camera should evolve between the two keyframes.
Optional synchronized audio
Generate matching audio for early sound, ambience, effects, music, or dialogue tests.
Flexible duration
Choose a draft video duration from 5 to 20 seconds.
Multiple aspect ratios
Supports landscape, portrait, square, and cinematic formats.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the action or transformation connecting the start and end images, including camera movement, timing, mood, lighting, and style. |
| start_image | Yes | Image used as the first visual keyframe. |
| end_image | Yes | Image used as the final visual keyframe. |
| aspect_ratio | No | Output aspect ratio. Options: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16. |
| duration | No | Draft video duration in seconds. Range: 5–20. Default: 5. |
| generate_audio | No | Generate synchronized audio for the draft transition. Default: true. |
5 to 20 seconds.generate_audio when you want to test ambience, effects, music, or dialogue.Pricing is based on billed video duration.
Billed duration is rounded up to the next whole second and capped at 20 seconds. The API accepts durations from 5 to 20 seconds. Audio generation does not add a separate charge.
| Billing Unit | Price |
|---|---|
| Per 5s | $0.30 |
| Per second | $0.06 |
| Duration | Billed Duration | Cost |
|---|---|---|
| 5s | 5s | $0.30 |
| 10s | 10s | $0.60 |
| 15s | 15s | $0.90 |
| 20s | 20s | $1.20 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/start-end-to-video-draft with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Flux 3 Start End To Video Draft below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"start_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"end_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"aspect_ratio": "21:9",
"duration": 5,
"generate_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/start-end-to-video-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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/start-end-to-video-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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"start_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"end_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"aspect_ratio": "21:9",
"duration": 5,
"generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"start_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"end_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"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/start-end-to-video-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 Start End To Video Draft is a Black Forest Labs model for video generation from images, exposed as a REST API on WaveSpeedAI. FLUX 3 Start-End-to-Video Draft quickly generates a transition between required start and end images, with prompt-guided motion, optional synchronized audio, and flexible 5-20 second duration for rapid keyframe iteration. 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/black-forest-labs/black-forest-labs-flux-3-start-end-to-video-draft.
Flux 3 Start End To Video Draft 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.
Key inputs: `prompt`, `aspect_ratio`, `duration`, `end_image`, `generate_audio`, `start_image`. 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-start-end-to-video-draft.
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.
Commercial usage rights depend on the model's license, set by its provider (Black Forest Labs). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.