Wan 2.6 Flash Reference to Video

Name: Wan 2.6 Flash Reference to Video
Author: Alibaba

alibaba/wan/2.6/flash/reference-to-video

Alibaba Wan 2.6 Flash reference-to-video model that places characters from reference images or videos into a new scene, with optional generated audio and multi-shot control.

Use in agent Get API key

Base price: $0.25USD / run
Execution: async
Model type: video
Input fields: 9

Production route

Try the model

Playground

Open playground

Input

Prompt(string)

Use Character1, Character2, etc. to reference subjects from your reference files. Works for people, animals, or objects. For multi-shot prompts: '[0-3s] Shot 1. [3-6s] Shot 2.' Max 1500 characters. Reference order: video_urls first, then image_urls.

Images(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

Reference images for subject consistency (0-5 images). Combined with video_urls, total references cannot exceed 5. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP. Resolution: 240-5000px. Max 10MB each. Reference order: image_urls continue numbering after video_urls.

Videos(array)

Reference videos for subject consistency (0-3 videos). Videos' FPS must be at least 16 FPS. Combined with image_urls, total references cannot exceed 5. Reference order: video_urls are numbered first (Character1, Character2...), then image_urls continue the sequence.

Resolution(string)

Video resolution tier. R2V Flash only supports 720p and 1080p. Allowed values: 720p, 1080p.

Duration(integer)

Duration of the generated video in seconds. R2V Flash supports only 5 or 10 seconds. Allowed values: 5, 10.

Multi Shots(boolean)

When true (default), enables intelligent multi-shot segmentation for coherent narrative videos with multiple shots. When false, generates single continuous shot. Only active when enable_prompt_expansion is True.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 16:9, 9:16, 1:1, 4:3, 3:4.

Seed(integer)

Random seed for reproducibility. If None, a random seed is chosen.

Generate Audio(boolean)

Whether to generate a video with audio. Set to false for silent video generation. Silent videos are faster and cost 25% of the audio version price.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.25 / run
Billing formula: ((params.duration ?? 5) + (len(params.videos ?? []) > 0 ? 5 : 0)) * ((params.generate_audio ?? true) ? ((params.resolution ?? "720p") == "1080p" ? 0.075 : 0.05) : ((params.resolution ?? "720p") == "1080p" ? 0.0375 : 0.025))

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Alibaba
Model ID: alibaba/wan/2.6/flash/reference-to-video
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Wan 2.6 Flash Reference to Video

Wan 2.6 Flash Reference to Video delivers the faster Wan 2.6 character-reference workflow for short-form production. It preserves the core multi-character reference behavior while prioritizing turnaround, making repeated casting, staging, and interaction experiments practical before a slower final render is selected.

Use clear single-subject references, identify them consistently in the brief, and keep the interaction easy to stage. The Flash model suits social clips, dialogue blocking, mascot variations, and high-volume tests where subject identity matters but creative teams need more iterations within the same review window.

Highlights

Rapid reference-character generation. Produces multi-character reference-led clips through a speed-optimized inference path.
Mixed image and video casting. Accepts visual references that define the protagonists appearing in a new scene.
Fast interaction prototyping. Lets teams compare actions, staging, and camera ideas without a long generation cycle.
Optional silent creation. Can generate without sound when the moving picture will enter a separate audio workflow.

Pricing

Duration	Audio	720p	1080p
5 seconds	on	$0.250	$0.375
5 seconds	off	$0.125	$0.188
10 seconds	on	$0.500	$0.750
10 seconds	off	$0.250	$0.375

When reference videos are supplied, Alibaba also bills their duration (capped at 5 seconds), so 5 seconds are added to the billed duration.

When to Use

✅ Good fit	❌ Consider alternatives
The project needs this exact reference-to-video workflow	The intended task belongs to a different media route
Available source media matches every required field	Required assets or usage rights are unavailable
The brief can define subject, action, camera, and style	Output must be deterministic at frame or pixel level
Supported duration, resolution, and framing fit delivery	Final placement requires unsupported specifications
An asynchronous generation job fits production	A live or frame-synchronous response is mandatory

Prompt Guide

Describe the result as a shot or design brief: identify subjects and references, state the action or transformation, specify environment and composition, then add camera behavior, lighting, pacing, style, sound, and preservation constraints where relevant. Use exact reference identifiers exposed by the local schema.

{
  "images": [
    "https://example.com/reference-1.png",
    "https://example.com/reference-2.png"
  ],
  "prompt": "A cinematic scene with clearly directed subject action, camera movement, lighting, pacing, and atmosphere",
  "seed": 1,
  "videos": [
    "https://example.com/reference.mp4"
  ]
}

Technical Specs

Spec	Value
Model ID	`alibaba/wan/2.6/flash/reference-to-video`
Input fields	`seed` (integer)<br>`images` (array)<br>`prompt` (string)<br>`videos` (array)<br>`duration` (integer; `5`, `10`)<br>`resolution` (string; `720p`, `1080p`)<br>`multi_shots` (boolean)<br>`aspect_ratio` (string; `16:9`, `9:16`, `1:1`, `4:3`, `3:4`)<br>`generate_audio` (boolean)
Required input	`prompt`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

alibaba/wan/2.6/reference-to-video — Compare this concrete local family route.
alibaba/wan/2.6/text-to-image — Compare this concrete local family route.
alibaba/wan/2.6/image-to-image — Compare this concrete local family route.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

alibaba/wan/2.6/flash/reference-to-video

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "alibaba/wan/2.6/flash/reference-to-video",
  "images": [
    "https://static.sandbase.ai/examples/alibaba/wan/2.6/reference-to-video/flash/input_images_0.png"
  ],
  "prompt": "Dance battle between Character1 and Character2.",
  "videos": [
    "https://static.sandbase.ai/examples/alibaba/wan/2.6/reference-to-video/flash/input_videos_1.mp4"
  ],
  "duration": 5,
  "resolution": "720p",
  "multi_shots": true,
  "aspect_ratio": "16:9",
  "generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
Wan 2.6 Flash Reference to VideoThis model `Alibaba`	Video	$0.25 / run	Feb 6, 2026
Wan 2.7 Video Edit `Alibaba`	Video	$0.50 / run	Oct 5, 2026
Wan 2.7 Video Extend `Alibaba`	Video	$0.50 / run	Oct 5, 2026
Wan 3.0 Prime Video Edit `Alibaba`	Video	$1.40 / run	Oct 4, 2026
Wan 3.0 Prime Video Extend `Alibaba`	Video	$0.70 / run	Oct 4, 2026
Wan 3.0 Video Edit `Alibaba`	Video	$1.00 / run	Oct 4, 2026

Questions

FAQ

How do I call Wan 2.6 Flash Reference to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/wan/2.6/flash/reference-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate Alibaba account?

No. One SandBase API key and balance gives you access to Wan 2.6 Flash Reference to Video and the other models in the catalog; you do not need to sign up with Alibaba separately.