Wan 2.6 Flash Reference to Video
alibaba/wan-2.6-flash/reference-to-video
Generate a 2–10 second video using reference images or videos, with optional audio at 720P or 1080P.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 1500 chars | Prompt describing the video, supports Chinese and English, up to 1500 characters. Refer to each reference as character1, character2, ... in file order; this is the only way the model identifies referenced characters. |
| audioGenerate Audio | boolean | true | — | On: outputs a video with audio (voices from reference videos can be preserved). Off: outputs a silent video at half the price. |
| durationDuration (s) | number | 5 | 2 ~ 10 · step 1 | Output video duration, an integer from 2 to 10 seconds |
| sizeResolution | select | 1920*1080 | 1920*1080 | 1080*1920 | 1440*1440 | 1632*1248 | 1248*1632 | 1280*720 | 720*1280 | 960*960 | … | Output video resolution (width*height). 1080P costs more than 720P. |
| shot_typeShot Type | select | single | single | multi | single: one continuous shot; multi: multiple cuts. This setting overrides shot descriptions in the prompt. |
| negative_promptNegative Prompt | textarea | — | ≤ 500 chars | Describe what should not appear in the video, up to 500 characters |
| prompt_extendEnable Prompt Expansion | boolean | true | — | If set to true, the prompt optimizer will be enabled. |
| seedSeed | number | — | 0 ~ 2147483647 · step 1 | For reproducibility, 0-2147483647. Leave empty for random. |
Output fields
| Field | Type | Description |
|---|---|---|
| videos | array<string> |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6-flash/reference-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "character1 turns gently toward the camera with natural movement and a subtle smile. Smooth cinematic lighting.",
"audio": true,
"duration": 5,
"size": "1920*1080",
"shot_type": "single",
"prompt_extend": true,
"seed": 12345
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6-flash/reference-to-video",
headers=HEADERS,
json={
"input": {
"prompt": "character1 turns gently toward the camera with natural movement and a subtle smile. Smooth cinematic lighting.",
"audio": True,
"duration": 5,
"size": "1920*1080",
"shot_type": "single",
"prompt_extend": True,
"seed": 12345
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6-flash/reference-to-video", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "character1 turns gently toward the camera with natural movement and a subtle smile. Smooth cinematic lighting.",
"audio": true,
"duration": 5,
"size": "1920*1080",
"shot_type": "single",
"prompt_extend": true,
"seed": 12345
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
Wan 2.6 Flash Reference to Video
alibaba/wan-2.6-flash/reference-to-video
Generate a 2–10 second video using reference images or videos, with optional audio at 720P or 1080P.
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
reference_urls | array | true | — | 1–5 reference files: up to 5 images and 3 videos. Array order maps to character1, character2, ... . Reference images are free; the full duration of each reference video is added to the output duration for billing. Images: JPEG/JPG/PNG (no alpha)/BMP/WEBP, 240–8000 px, up to 20MB. Videos: MP4/MOV, 1–30 seconds, up to 100MB.; 1–5 URLs |
prompt | string | true | — | Prompt describing the video, supports Chinese and English, up to 1500 characters. Refer to each reference as character1, character2, ... in file order; this is the only way the model identifies referenced characters.; max 1500 characters |
audio | boolean | false | true | On: outputs a video with audio (voices from reference videos can be preserved). Off: outputs a silent video at half the price. |
duration | integer | false | 5 | Output video duration, an integer from 2 to 10 seconds [2, 10]; integer |
size | string | false | "1920*1080" | Output video resolution (widthheight). 1080P costs more than 720P. 19201080, 10801920, 14401440, 16321248, 12481632, 1280720, 7201280, 960960, 1088832, 832*1088 |
shot_type | string | false | "single" | single: one continuous shot; multi: multiple cuts. This setting overrides shot descriptions in the prompt. single, multi |
negative_prompt | string | false | — | Describe what should not appear in the video, up to 500 characters; max 500 characters |
prompt_extend | boolean | false | true | If set to true, the prompt optimizer will be enabled. |
seed | integer | false | — | For reproducibility, 0-2147483647. Leave empty for random. [0, 2.14748e+09]; integer |
Pricing
Total price = unit rate × ceil(output duration + sum of full reference video durations). Round up once after adding all durations, not per video. Reference images add no duration or fee. This policy uses full reference durations; it does not use a fixed 5-second surcharge or Alibaba reference-duration truncation.
| Resolution | audio=true USD/s | audio=false USD/s |
|---|---|---|
| 720P | $0.05 | $0.025 |
| 1080P | $0.075 | $0.0375 |
Defaults: 1080P, 5 output seconds. With image-only references the price is $0.375 (37.5 credits), audio=true; $0.1875 (18.75 credits), audio=false.
Example: one 10-second reference video and a 5-second output are billed as 15 seconds. Reference order maps to character1, character2, ... . USD 1 = 100 credits; account discounts are applied separately.
720P: 1280*720, 720*1280, 960*960, 1088*832, 832*1088.
1080P: 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632.
Flash unit rates use Alibaba International USD pricing; duration billing follows the full-reference-duration policy described above.
API
curl -X POST https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6-flash/reference-to-video \
-H "Authorization: Bearer $API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"input": {
"audio": true,
"duration": 5,
"size": "1920*1080",
"shot_type": "single",
"prompt_extend": true,
"reference_urls": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/08/31/0d2b8fc70ea0.jpeg"
],
"prompt": "character1 turns gently toward the camera with natural movement and a subtle smile. Smooth cinematic lighting.",
"seed": 12345
}
}'
curl 'https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID' \
-H "Authorization: Bearer $API_KEY"
Poll task_uuid until completed or failed. Successful output.videos contains video URL strings.
Related models
xAI Grok Imagine Video v1.5 Reference to Video
Generate a 1-15 second video from a prompt and 1-7 reference images at 480p or 720p.
Vidu Q4 Preview Reference to Video
Generate a 3–16 second video from a prompt with optional references: up to 15 images and 3 audio clips. Supports aspect ratio selection, audio generation and 540p–4k resolution.
MiniMax H3 Reference to Video
MiniMax H3 Reference to Video generates coherent 2K videos from natural-language prompts and multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Gemini Omni Flash Reference to Video API
Gemini Omni Flash Reference to Video creates short AI videos with synchronized audio from one or more reference images and a text prompt, preserving visual identity and following the provided references for guided multimodal video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Seedance 2.0 Mini Reference to Video
Seedance 2.0 Mini Reference-to-Video is a high-speed, cost-effective video generation model developed by ByteDance, engineered specifically for creating multi-shot videos with a cinematic feel. By seamlessly combining reference images with text prompts, it generates highly narrative video segments. The model features advanced AI camera control and ensures robust character consistency across different scenes. It supports multiple output resolutions from 480P up to 4K, durations ranging from 4 to 15 seconds, and flexible aspect ratios. Complete with an out-of-the-box REST inference API, it delivers exceptional performance with zero cold starts, offering an affordable yet premium solution for professional video creation.
Seedance 2.5 Reference to Video
The "Reference-to-Video" feature of Seedance 2.5 is the ultimate solution for visual stylistic unity. It precisely extracts artistic styles, lighting tones, or compositional intents from reference materials and seamlessly integrates them into newly generated videos, ensuring a highly consistent visual language for your creative series.
Seedance 2.0 Fast reference-to-video
Seedance 2.0 Fast (Video-Edit) edits an input video from a natural-language prompt at a faster, cheaper tier. Built on ByteDance Seed's unified multimodal architecture, it preserves subject identity, composition, and motion while rewriting lighting, style, weather, environment, or specific elements as instructed. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.