WanAI image & video generation by Alibaba Cloud

Wan is an AI generation tool/model under Alibaba Cloud's Tongyi system, designed for visual creation (images/videos). By inputting text prompts or uploading images, users can generate stylized and creative images or short videos. It possesses multimodal capabilities (text ↔ image ↔ video) and provides developers with API interfaces, enabling integration into other products and services. Its development is expanding from image generation to video generation, audio-visual synchronization, dubbing, and more.

freemium

Text to ImageAI Video Generation

IndexedOctober 14, 2025

UpdatedApril 16, 2026

4.0 (0 Number of reviews)

It supports various visual creation capabilities such as text-to-image, image-to-image, image editing / style transfer, and image-to-video / text-to-video.

What is Wan

Tongyi Wanxiang is an AI creative visual generation platform/model under Alibaba/Alibaba Cloud's "Tongyi" ecosystem, primarily used for image and video creation.

It supports various visual creation capabilities such as text-to-image, image-to-image, image editing / style transfer, and image-to-video / text-to-video.

Technically, Tongyi Wanxiang belongs to the category of multimodal large models (focusing on visual/image/video domains), utilizing prompts and input images as conditions to achieve content generation.

Throughout its development, the Tongyi Wanxiang project has undergone version iterations (such as Wanxiang 2.1, 2.2, 2.5, etc.) to enhance video generation capabilities, support audio, improve effects, and more.

For example, its image-to-video model supports generating short videos (5-10 seconds, specified resolution, optional voiceovers, etc.) based on the first-frame image and text prompts.

Tongyi Wanxiang has been in a "free internal testing/invitation-only trial" phase during certain periods, and public accessibility may be limited.

Pros & Cons

Pros

Supports both image and video generation from text/images.
Provides API for developers to integrate into applications.
Backed by Alibaba Cloud's reliable infrastructure.
Continuously updates with new features like audio sync.

Cons

Free tier has limited credits; heavy usage requires payment.
Output quality may vary for complex prompts.
Requires internet connection; no offline mode.

Frequently Asked Questions

Is Tongyi Wanxiang free to use?

Tongyi Wanxiang offers a free tier with limited monthly credits for image and video generation, but advanced features or higher usage may require paid plans. Check Alibaba Cloud's official page for exact quotas.

What kind of content can I generate with Tongyi Wanxiang?

You can generate images from text prompts, transform images into new styles, create short videos from text or images, and even sync audio with video. It supports multimodal creation.

Who is Tongyi Wanxiang suitable for?

It's ideal for designers, content creators, marketers, and developers who need AI-powered visual assets for projects, social media, or product demos. The API also suits enterprises integrating AI into their workflows.

How does Tongyi Wanxiang compare to other AI art tools?

Tongyi Wanxiang benefits from Alibaba Cloud's infrastructure, offering robust API access and integration with other Alibaba services. It supports both image and video generation, while some competitors focus on images only.

Explore More

Similar Tools

StoryIntoVideo

StoryIntoVideo is an AI-powered video generation tool that lets users convert any text—be it a novel, script, or narrative—into short videos complete with characters, scenes, and voiceovers. It significantly lowers the barrier to video production, making it ideal for content creators, authors, and marketers looking to quickly visualize their stories.

ShortFast

ShortFast is an AI-powered automation tool designed for YouTube Shorts and TikTok. It automatically generates viral-ready scripts and matches them with suitable stock video footage, enabling fully automated video production. It's ideal for creators and marketers who need to produce high volumes of content efficiently.

VidFlux

VidFlux is an AI-powered tool that transforms static images into dynamic, cinematic videos with realistic motion and depth. By intelligently analyzing image content, it automatically generates smooth camera movements, giving your photos a professional, film-like quality. It's perfect for social media creators, marketers, and photography enthusiasts looking to quickly produce engaging visual content.

Kairval

Kairval is an AI video generation tool that lets users create cinematic clips, animations, and short videos from simple text prompts. Leveraging advanced AI video models, it transforms written descriptions into visual content, making it ideal for content creators, marketers, and video enthusiasts. Produce stunning video works in minutes without needing professional video editing skills.

AI Video Maker

A browser-based online video generation platform, primarily focused on quickly creating short videos from text scripts, suitable for users who need to produce social media content in bulk but lack editing skills.

Wuli

Wuli is an AI creation tool centered on "rapid generation of usable images and video content." Unlike platforms that offer only a single generation capability, Wuli integrates image and video creation into a unified workflow, making it suitable for creators who need to frequently produce materials. (Currently, it only supports Chinese and users in China.)

Open-source Alternatives

ArcReel: Open-Source AI Video Workbench for Novel-to-Video

ArcReel is an open-source AI Agent-based video generation workbench that automatically converts novels into characters, scenes, props, then generates screenplays, storyboards, and eventually composes videos. It maintains character and scene consistency across shots using cross-shot consistency technology, supporting models like Veo 3.1, Grok, and Seedance. Ideal for content creators and developers.

MoneyPrinterTurbo: AI Short Video Generation Tool

Primarily used for automatically generating short videos, it connects tasks such as script generation, voice-over, video material splicing, and video output. It is closer to a "pipeline-style content generation tool."

Wan2.2: AI Video Generation & Synthesis Framework

It is an AI model library/framework for video generation/video synthesis/text/image → video, supporting multiple tasks (Text → Video, Image → Video, Text+Image → Video, etc.)

Jaaz: Open-source AI for Creative Content Design

Jaaz is an open-source tool/platform/framework designed for creative, image, video, layout design, and multimodal content creation. It aims to empower users to create (images, videos, canvas designs, prompt auto-optimization, etc.) in a more flexible and controllable manner within local or hybrid environments.

InfiniteTalk: AI Speech Video Generation Tool

A "limitless speech video generation tool" launched by the MeiGen‑AI team, supporting both image-to-video and video-to-video modes.