WAN 2.6 Reference-to-Video Flash turns character, prop, or scene references from images or videos into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Flash version with faster generation speed. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
待機中
$0.1251回あたり·~80 / $10
The man in the image is walking on the moon. He says, "The earth is so beautiful!".
The woman in picture 1 and the man in picture 2 are sitting in the school cafeteria eating. The girl asks the boy, "Why are you looking at me?" Then, both of them laugh. With natural background music added.
Make the woman in the reference video put on a jacket and sunglasses. And say, "Oh, it's cold!"
Wan 2.6 Reference-to-Video Flash is fast reference-driven video generation model. Upload up to 5 reference images and describe the scene — the model generates high-quality video that preserves character identity and appearance, with optional audio generation and multi-shot support.
Multi-reference input Upload up to 5 reference images for precise character and scene guidance.
Identity preservation Maintains character appearance and identity across generated video frames.
Audio generation Optional synchronized audio for complete video output.
Shot type control Choose between single continuous shot or multi-shot composition.
Multiple resolutions Support for 720p and 1080p in both landscape and portrait orientations.
Prompt Enhancer Built-in tool to automatically improve your video descriptions.
| Parameter | Required | Description |
|---|---|---|
| reference_urls | Yes | Reference images (1-5, click "+ Add Item" for multiple) |
| prompt | Yes | Text description of the video scene and motion |
| audio | No | Custom audio track (URL or upload) |
| negative_prompt | No | Elements to exclude from generation |
| size | No | Output size: 1280720, 7201280, 19201080, 10801920 |
| duration | No | Video length: 5 or 10 seconds (default: 5) |
| shot_type | No | Shot composition: single, multi (default: multi) |
| enable_audio | No | Generate synchronized audio (default: enabled) |
| enable_prompt_expansion | No | Enable prompt optimizer (default: disabled) |
| seed | No | Random seed for reproducibility (-1 for random) |
Pricing depends on resolution, duration, and audio settings.
| Size | Duration | Audio Off | Audio On |
|---|---|---|---|
| 720p | 5s | $0.25 | $0.50 |
| 720p | 10s | $0.375 | $0.75 |
| 1080p | 5s | $0.40 | $0.80 |
| 1080p | 10s | $0.60 | $1.20 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/reference-to-video-flash with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 2.6 Reference To Video Flash below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"reference_urls": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5,
"shot_type": "single",
"enable_audio": true,
"enable_prompt_expansion": false,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/reference-to-video-flash" \
-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/alibaba/wan-2.6/reference-to-video-flash";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"reference_urls": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5,
"shot_type": "single",
"enable_audio": true,
"enable_prompt_expansion": false,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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 = {
"reference_urls": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 5,
"shot_type": "single",
"enable_audio": True,
"enable_prompt_expansion": False,
"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/alibaba/wan-2.6/reference-to-video-flash", 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 2.6 Reference To Video Flash is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.6 Reference-to-Video Flash turns character, prop, or scene references from images or videos into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Flash version with faster generation speed. 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/alibaba/alibaba-wan-2.6-reference-to-video-flash.
Wan 2.6 Reference To Video Flash starts at $0.13 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`, `audio`, `duration`, `size`, `seed`, `negative_prompt`. 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/alibaba/alibaba-wan-2.6-reference-to-video-flash.
Median end-to-end generation time on WaveSpeedAI is around 68 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 (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.