Wan AI: Wan 2.7 Reference-to-Video
wan-ai/wan2.7-r2v
Access Wan 2.7 Reference-to-Video from Wan AI using the Puter.js AI API for free.
Get Started
Model Card
Wan 2.7 Reference-to-Video is a diffusion-based video generation model from Alibaba that builds a scene from reference images and videos rather than a single starting frame. It is part of the same four-model Wan 2.7 suite as text-to-video, image-to-video, and video editing, and it shares their native 720p and 1080p output at 30fps.
It accepts reference images and reference videos, up to five items combined, letting a character, prop, or visual style carry over consistently into a new generated scene. This supports single-shot and multi-shot sequences, including scenes with multiple characters interacting, and produces clips from 2 to 10 seconds, a shorter ceiling than the image-to-video and text-to-video models in the suite.
It suits keeping a recurring character consistent across a series of clips, a brand mascot appearing in multiple scenes, or any production where visual consistency between shots matters more than generating each shot independently.
Max Duration N/A
seconds
Frame Rate N/A
fps
Aspect Ratio N/A
supported
Release Date Apr 3, 2026
Code Example
Use Wan 2.7 Reference-to-Video in your app with the Puter.js AI API — no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.txt2vid("A cat playing with a ball of yarn", {
model: "wan-ai/wan2.7-r2v"
}).then(video => {
document.body.appendChild(video);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.txt2vid("A cat playing with a ball of yarn", {
model: "wan-ai/wan2.7-r2v"
}).then(video => {
document.body.appendChild(video);
});
</script>
</body>
</html>
More AI Models From Wan AI
Wan 2.7 Text-to-Video
Wan 2.7 Text-to-Video is a diffusion-based video generation model from Alibaba, designed to produce cinematic video clips directly from text prompts. It generates native 720p and 1080p video with durations from 2 to 15 seconds, supporting flexible aspect ratios including 16:9, 9:16, and 1:1. A standout feature is optional audio input, which synchronizes character motion and lip movement to a provided audio track during generation. The model responds well to detailed, structured prompts and supports multi-shot narrative control through prompt language alone. It's part of a broader four-model suite that includes image-to-video, reference-to-video, and video editing capabilities. Best suited for marketing content, social media clips, film pre-visualization, and any production pipeline that needs programmatic access to high-quality video generation.
VideoWan 2.7 Image-to-Video
Wan 2.7 Image-to-Video is a diffusion-based video generation model from Alibaba that animates a still image into motion instead of generating a scene purely from text. It is part of the same four-model Wan 2.7 suite as text-to-video, reference-to-video, and video editing, and it shares their native 720p and 1080p output at up to 30fps. Where the text-to-video model starts from a written prompt alone, this one takes an input image as the starting or ending frame, supporting first-frame, first-and-last-frame interpolation, and shot continuation, plus 3x3 grid-to-video storyboarding for multi-panel sequences. It also accepts optional audio input for lip-synced motion and generates clips from 2 to 15 seconds. It suits animating product photos, extending an existing shot, or turning a storyboard into a rough cut without switching tools mid-pipeline.
ImageWan2.6 Image
Wan 2.6 Image is a 20-billion-parameter diffusion-based image generation and transformation model developed by Alibaba Cloud. Built on a Multimodal Diffusion Transformer (MMDiT) architecture, it supports text-to-image generation, image-to-image editing, and multi-reference style transfer. The model accepts up to three reference images per request, allowing developers to explicitly control style, subject, and composition by referencing inputs in the prompt (e.g., "image 1" for style, "image 2" for background). It generates outputs up to 2048×2048 pixels across a wide range of aspect ratios. Wan 2.6 Image is particularly strong at localized content generation, with sophisticated understanding of Asian cultural contexts and aesthetics. It's well suited for e-commerce product visualization, brand asset creation, marketing materials, and automated content pipelines where controllability and visual consistency matter more than pure artistic exploration.
Frequently Asked Questions
You can access Wan 2.7 Reference-to-Video by Wan AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required.
Integrating Wan 2.7 Reference-to-Video through the Puter.js AI API is free under the User-Pays Model. Each user pays for their own AI usage through their Puter account.
Wan 2.7 Reference-to-Video was created by Wan AI and released on Apr 3, 2026.
Yes — the Wan 2.7 Reference-to-Video API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Wan 2.7 Reference-to-Video to your app for free
Developers can integrate Wan 2.7 Reference-to-Video for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.