|
Listen to this story
|
MiniMax was launched as a text-to-video generator by a Chinese startup bearing the same name. The company recently launched its first model, Video-01. This model is designed to create high-resolution videos from text prompts. It operates at a native resolution of 1280 x 720 pixels and can generate videos at 25 frames per second.
Currently, the maximum video length is limited to six seconds, with plans to extend this to ten seconds in the future.
During an interview, founder Yan Junjie mentioned that the company had made significant progress in video generation. However, the specific parameters and technical details of the model have not been disclosed yet.
“We have indeed made significant progress in video model generation, and based on internal evaluations and scores, our performance is better than Runway,” Junjie said.
The current model is the initial version, with an updated version expected soon. As of now, it offers text-to-video capabilities, with future plans to include image-to-video and text-plus-image generation features.
Founded in 2021 by former employees of SenseTime, including Junjie. The startup is backed by Alibaba and Tencent.
Here, we delve into some of the best videos generated by MiniMax.
Magic coin
The company released an official 2-minute AI film titled ‘Magic Coin’ generated entirely by its large model, showcasing a coin that appears and disappears within a person’s hand, illustrating the tool’s capability to seamlessly integrate AI-generated elements into real-world footage. This technology highlights the rapid advancements in AI video generation and its potential applications across various industries, including entertainment, advertising, and visual effects.
Cats eat fish, dogs eat meat
The MiniMax video contrasts the natural instincts of cats and dogs, with cats favouring fish and dogs preferring meat, while the camera slowly pans towards a robotic figure appearing at the window. The figure then watches the animals for a brief few seconds.
The video uses clever animations or real-life footage to highlight how each animal reacts to its favourite food.
Man eating fast food
Here, it portrays a man indulging in a burger, capturing the rush and satisfaction of a quick meal against the backdrop of a food court. The video uses visuals and humorous elements to emphasise the speed at which the man consumes his food, reflecting a common modern-day scenario.
This highlights the advanced visual capabilities of AI in capturing and rendering detailed environments.
Teenager skateboarding
The video showcases a teenager skateboarding through the city, highlighting the thrill and skill involved in navigating the streets, with dynamic camera angles and fast-paced editing. It also features iconic city landmarks, adding to the sense of adventure and exploration.
Classical beauty applying lipstick
As the blurred camera comes back into focus, it features a beautiful Asian woman applying lipstick in her room. The video emphasises the delicate, precise motions as she applies the lipstick, with soft lighting and close-up shots showcasing her beauty. The room’s décor enhances the aesthetic appeal, reflecting a sense of elegance that might evoke royalty.
Pixel style
Amid the busy street in a bustling city, all rendered in pixel art style, a small cat walks by, weaving through the pixelated crowd and traffic. It cleverly contrasts the lively urban environment with the calm, making the cityscape vibrant and the cat’s presence even more striking.
The precise features and seamless editing add to future creativity in AI.
Futuristic high-tech lab
Set in a futuristic high-tech lab, this MiniMax video shows a woman engaging in a conversation with a holographic figure. The sleek, advanced technology is highlighted with the hologram, possibly representing an AI or digital assistant, interacting fluidly with the woman, suggesting a seamless integration of human and machine communication.
Blade Runner Cyber City
It begins with a sweeping view of a cyber city, characterised by towering skyscrapers, neon lights, and a vibrant, futuristic atmosphere. As the camera slowly shifts, it focuses on a man eating ramen at a roadside food truck, creating an intriguing contrast between the high-tech surroundings and the simplicity of street food.
This scene emphasises the coexistence of advanced technology and everyday human experiences.
Silver 1977 Porsche 911
Featuring a sleek, silver 1977 Porsche 911 Turbo cruising through a vibrant cyberpunk landscape, the car’s classic design contrasts strikingly with the futuristic, neon-drenched cityscape surrounding it. The video showcases the vehicle’s smooth motion against the backdrop of glowing backdrops, towering skyscrapers, and bustling streets.
The contrast of the vintage car with the high-tech environment highlights a blend of old-world charm and futuristic aesthetics.
Wig and sunglasses
A sad, bald man appears dejected and downcast. As the scene progresses, he puts on a wig and sunglasses, which instantly transform his mood. The video captures his transition from sadness to joy, highlighting the cheerful change in his expression and posture.
AI ensures that each gesture and reaction is natural, enhancing the viewer’s engagement and the characters’ believability.
