Available now

Wan 2.6 Flash: video from references

By Alibaba

Wan 2.6 Flash brings a photo to life as the first frame of a clip, or puts people and objects from your reference videos and images into a new scene, with sound.

Model ID
Maker
Alibaba

Model id

Use this in every request
wan/v2.6/reference-to-video/flash

This model has other modes with their own ids: wan/v2.6/image-to-video/flash.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/v2.6/reference-to-video/flash",
  "input": {
    "prompt": "Character1 and Character2 walk side by side through an autumn park, kicking up leaves. [0-3s] Wide shot of the path. [3-5s] Close-up as Character1 laughs."
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "wan/v2.6/reference-to-video/flash", "quote_id": "QUOTE_ID", "input": {"prompt":"Character1 and Character2 walk side by side through an autumn park, kicking up leaves. [0-3s] Wide shot of the path. [3-5s] Close-up as Character1 laughs."}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for wan/v2.6/reference-to-video/flash
NameTypeDescription
promptrequiredstring
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.
video_urlsarray of image URLs
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.
image_urlsarray of image URLs
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.
aspect_ratiostring (enum)
The aspect ratio of the generated video.

Default: 16:9

One of: 16:9, 9:16, 1:1, 4:3, 3:4

resolutionstring (enum)
Video resolution tier. R2V Flash only supports 720p and 1080p.

Default: 1080p

One of: 720p, 1080p

durationstring (enum)
Duration of the generated video in seconds. R2V Flash supports only 5 or 10 seconds.

Default: 5

One of: 5, 10

negative_promptstring
Negative prompt to describe content to avoid. Max 500 characters.
enable_prompt_expansionboolean
Whether to enable prompt rewriting using LLM.

Default: true

multi_shotsboolean
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.

Default: true

generate_audioboolean
Whether to generate a video with audio. Set to false for silent video generation.

Default: true

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

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt
"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

  • 720p$0.1585/ second
  • 1080p$0.2377/ second

The exact charge for your input comes from a quote. How charges settle

API docs

About this model

Overview

The image mode starts from your picture and makes 5, 10 or 15 seconds at 720p or 1080p. Every clip comes with generated sound; you can also add a WAV or MP3 of 3 to 30 seconds as background music, cut to the clip length.

The reference mode takes up to 3 videos and up to 5 images, 5 references in all, and calls them Character1, Character2 and so on, videos first. It makes 5 or 10 seconds in 16:9, 9:16, 1:1, 4:3 or 3:4, and splits the story into shots unless you turn that off.

What you can build

  • A product or portrait photo brought to life at 1080p
  • Scenes that bring two people or pets from separate clips together
  • Short story clips cut into timed shots
  • Clips set to your own music track

Prompting tips

  • Name each reference by its number in the prompt, for example "Character1 hands Character2 a cup"; videos are counted before images.
  • Time the shots yourself in the prompt, for example "[0-3s] Shot 1. [3-6s] Shot 2.", or switch multi-shot off for one continuous take.
  • Multi-shot only works with prompt expansion on; turn both off when the model must follow your exact words.
  • Reference videos need at least 16 frames per second.

What to check

Check that each subject still matches its reference, that cuts land where you planned them, and that the sound carries through the ending.

Inputs

  • Prompt (required): 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.
  • Videos (optional): Reference videos for subject consistency (0-3 videos). Videos' FPS must be at least 16 FPS.
  • Images (optional): Reference images for subject consistency (0-5 images). Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP. Resolution: 240-5000px. Max 10MB each.
  • Aspect Ratio (optional): The aspect ratio of the generated video. Options: 16:9, 9:16, 1:1, 4:3, 3:4.
  • Resolution (optional): Video resolution tier. R2V Flash only supports 720p and 1080p. Options: 720p, 1080p.
  • Duration (optional): Duration of the generated video in seconds. R2V Flash supports only 5 or 10 seconds. Options: 5, 10.
  • Negative Prompt (optional): Negative prompt to describe content to avoid. Max 500 characters.
  • Enable Prompt Expansion (optional): Whether to enable prompt rewriting using LLM.
  • Multi Shots (optional): When true (default), enables intelligent multi-shot segmentation for coherent narrative videos with multiple shots. When false, generates single continuous shot.
  • Seed (optional): Random seed for reproducibility. If None, a random seed is chosen.

Output and limits

  • Length: 5 seconds to 10 seconds.
  • Resolutions: 720p, 1080p.
  • Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 720p: $0.1585 / second
  • 1080p: $0.2377 / second
  • The total for your settings is rounded up to the next cent.