Magi Model: Automatically Transcribing Manga into Text and Generating Scripts

Master Gemini AI in Claude Code: Ask, Review, and Brainstorm All in One Place

An innovative project is closely integrating Claude Code with Google's Gemini AI to enable powerful AI collaboration and offer developers an unprecedented programming experience. Through this integration, users will be able to directly ask Gemini questions, get code reviews, and brainstorm within the Claude Code environment, greatly enhancing development efficiency and code quality. The powerful functions of Gemini AI are now within reach.

MAGI-1, the World's First Autoregressive Video Generation Model, Officially Launched; Swin Transformer Team Leads a New Wave in Video Creation

A powerful new contender has emerged in the field of video generation—MAGI-1. Developed by Sand AI, a startup led by Cao Yue, winner of the Marr Prize and Tsinghua University's Special Award, this autoregressive video generation model is redefining the possibilities of video creation. MAGI-1 generates videos by predicting sequences of video blocks, garnering significant attention for its natural and fluid results and multiple downloadable versions. MAGI-1 boasts superior performance in video generation. Firstly, it delivers a seamless and smooth video experience, capable of generating...

Sand AI Open-Sources MAGI-1 Video Generation Model: Infinite Scalability, High Fidelity

On April 21, 2025, Sand AI open-sourced its video generation model, MAGI-1. With its innovative autoregressive diffusion architecture and exceptional performance, it quickly became a focal point in the generative AI field. Licensed under Apache 2.0, the code, weights, and inference tools are available on GitHub and Hugging Face, providing a powerful creative tool for global developers. MAGI-1 is based on a diffusion transformer architecture, incorporating block causal attention and parallel attention.

ChatGPT Updates Image Generation Capabilities, Now Including Cursive Script

ChatGPT's recent image generation update has driven a significant surge in paying users, with a 20-million increase reported. The creative applications showcased demonstrate impressive advancements in ChatGPT4.0's capabilities, even addressing previously challenging aspects like Chinese character generation. Now, ChatGPT has further enhanced its 'Creat image' function, moving beyond standard fonts to generate accurate cursive script.

Xiamen University Team Uses AI to Aid Oracle Bone Script Studies, Selected for 'Exploration Yuan Program 2024' TOP 10

Japan Plans to Use Artificial Intelligence to Combat Online Manga and Animation Piracy

The Japanese government recently announced a plan to utilize artificial intelligence technology to combat online manga and animation piracy. According to data from the Tokyo Bureau of Cultural Affairs, there are currently at least 1,000 websites illegally offering free downloads of Japanese manga and animation. These sites are accused of causing losses of billions of dollars to Japan's cultural industry each year. To address this issue, the Japanese government has proposed a pilot program totaling 300 million yen (approximately 2 million USD). This program will implement an image and text detection system, leveraging artificial intelligence technology to surveil the internet.

Cat's Eye Entertainment Launches Dynamic Storyboard AI Generation Tool 'Shenbi MALIANG' for Script Creation Automation

According to 36Kr, Cat's Eye Entertainment has released its first dynamic storyboard AI generation tool 'Shenbi MALIANG', aimed at long script analysis. This tool is specifically designed for long script analysis and provides great convenience for script creators. From the description, the functionalities of this AI tool are very powerful – simply upload the script to achieve one-click intelligent analysis, smart character creation, intelligent storyboard creation, intelligent dialogue reading, and more. Imagine, what used to require a considerable amount of time and effort for script conceptualization can now be done through 'Shenbi MALIANG'.

Kunlun Wanwei Launches the World's First AI Short Drama Platform SkyReels

On August 19, Kunlun Wanwei announced the launch of SkyReels, the world's first AI short drama platform, marking the official arrival of the 'one person, one drama' era. The SkyReels platform achieves full-process automation for script generation, character customization, storyboard creation, plot development, dialogue/background music, and video synthesis by integrating large video models and 3D models, allowing creators to easily produce high-quality AI videos with the click of a button.

Kuaishou's Keling Large Model Unveils Image-to-Video Feature with Continuation Capability of Up to 3 Minutes

Kuaishou announces that its Keling large model officially supports the image-to-video feature, along with an innovative video continuation function. This update allows users to easily transform static images into lively and engaging 5-second videos, with the ability to control the motion trajectory of objects in the image through text prompts.

Artificial Intelligence Powers a New Chapter of Osamu Tezuka's Classic Manga 'Black Jack'

Osamu Tezuka's 'Black Jack' enters a new chapter, showcasing collaboration between AI and humans. The large language model GPT-4 and AI image generator Stable Diffusion work together to develop storylines and character designs. Tezuka's son expressed that while not everyone is satisfied with the project, he hopes it sparks more discussions about AI in the creative field.