Hailuo, the free text-to-video generator released last month by the Alibaba-backed company MiniMax, has delivered its promised image-to-video feature. Founded by AI researcher Yan Junjie, the Shanghai-based MiniMax also has backing from Tencent. The model earned high marks for what has been called “ultra realistic” video, and MiniMax says the new image-to-video feature will improve output across the board as a result of “text-and-image joint instruction following,” which means Hailuo now “seamlessly integrates both text and image command inputs, enhancing your visuals while precisely adhering to your prompts.”

Hailuo “quickly gained a following among early adopter AI video creators for its vivid, coherent videos with human motions that were much more fluid and lifelike — often faster — than other rival video generators from U.S. companies such as Runway and Luma AI,” writes VentureBeat.

Tom’s Guide comments favorably on overall improvements in realism and response times, noting MiniMax “is rapidly building on the model, including launching a new dedicated English-language website and community.”

The MiniMax AI portfolio now features a suite of AI-driven products. One, the Music Generation Model, “allows users to create unlimited music tracks in various styles, offering flexibility to both casual users and professionals,” VentureBeat reports.

Additionally, Hailuo AI supports intelligent search, document summarization and voice communication. “These tools highlight MiniMax’s commitment to pushing the boundaries of AI technology across multiple industries,” VentureBeat opines.

The Xingye App is another MiniMax AI product, allowing users to generate customizable AI companions with which they can interact. “With flexible personalities and imaginative scenarios, the app allows for highly creative and personalized experiences, whether for entertainment or emotional engagement,” notes VB.

Hailuo, which creates 6-seconds of video at a time, made a splashy debut in September. MiniMax offers some interesting Hailuo clips on its website.

Tom’s puts the iteration through its paces, enthusing over results from prompts that test motion (an astronaut running through the dusty, low-gravity atmosphere of Mars), conversational motion (generated from a single image of a woman talking), and a dog frolicking on a beach. Everything from the inclusion of subtle, background motion to the color palettes earned approval from Tom’s.

Ars Technica points out that Kuaishou Technology’s Kling was another capable generative video model to emerge form China in the wake of OpenAI’s Sora debut in February.

“Both Chinese models have already powered numerous viral AI-generated video projects, accelerating meme culture in weird new ways,” Ars Technica observes.