AI Video Generation
MiniMax launches Hailuo 2.3 video model with enhanced motion and style support
MiniMax's Hailuo 2.3 video model improves motion rendering, expands style support for anime and CG, and delivers more natural facial expressions. The companion Media Agent lets users create videos from text, images, and audio with a single click.
Chinese AI startup MiniMax has released Hailuo 2.3, an upgraded version of its AI video generation model that promises more realistic motion, improved stylistic versatility, and enhanced facial animation. The update builds on the Hailuo 02 model introduced earlier this year and retains the same pricing for both enterprise and consumer tiers.
Key improvements in Hailuo 2.3
According to MiniMax, Hailuo 2.3 delivers markedly better rendering of complex human body movements, with smoother and more natural results. The model also shows improved compliance with motion-related prompts, enabling more accurate and controlled outputs. Lighting, shadow transitions, and color tones across dynamic camera shots now approach the quality of real-world footage.
The model offers expanded support for stylized content, including anime, illustrations, ink wash paintings, and game CGI, a move likely to appeal to creators in those domains. MiniMax notes that while its earlier Hailuo 01 Live model was popular among anime creators, Hailuo 2.3 unlocks a broader range of visual styles while maintaining stability and liveliness in outputs.
Facial expressions and object motion
MiniMax emphasized that Hailuo 2.3 produces more natural facial performances and micro-expression changes, creating more compelling character portrayals. The model also demonstrates better responsiveness to object motion instructions, a capability tested during China's Singles' Day shopping festival, where beta users generated e-commerce advertisements with reportedly higher success rates.
Pricing and performance
MiniMax claims Hailuo 2.3 sets a new global benchmark for cost-effectiveness among video generation models. The company has kept pricing unchanged from Hailuo 02 while improving performance. A faster variant, Hailuo 2.3 Fast, offers quicker generation at a lower price point, potentially reducing costs by up to 50% for batch production work.
The model is available across MiniMax's Hailuo AI web platform, mobile app, and open API. Free daily trial quotas are being provided during the launch period.
Media Agent: a full-modal creative suite
Alongside the model update, MiniMax introduced Media Agent, an evolution of the Hailuo Video Agent launched this summer. Media Agent supports full-modal creation, automatically matching text prompts, images, video clips, and audio without requiring manual editing. The tool's 'one-click to video' feature generates complete videos from user inputs.
For professional creators, Media Agent allows step-by-step composition with free uploads of images, video, or audio, with customization on demand. MiniMax demonstrated the feature by generating a 30-second advertisement for a fictional corn chip brand, 'Casa Nacho,' from a brief describing desired scenes, color tones, camera styles, and music.
Future updates to Media Agent will let users adjust any part of the output pipeline via a canvas interface, enabling 'conversation as creation', a workflow MiniMax believes represents the next generation of creative platforms.
Market context
The video generation AI space has grown increasingly competitive, with players including OpenAI's Sora, Runway, Pika, and Kuaishou's Kling vying for creators' attention. MiniMax's Hailuo 2.3 aims to differentiate by combining affordable pricing with support for a wide range of visual styles, particularly those popular in Asian markets such as anime and ink painting.
MiniMax stated that it will continue to optimize the model for specific video application scenarios and address real-world user feedback as part of its roadmap.