xAI has released Grok Imagine Video 1.5, a model that animates a still image into a short video clip. It generates synchronized audio during the same pass, combining visual animation and sound creation in one workflow. The Replicate Blog post focuses on prompting techniques intended to help users get more from the model.
遊戲與 AI 研發團隊 Overworld 在 Hugging Face 上推出了「Waypoint-1」。這是一項突破性的即時互動式影片擴散(Interactive Video Diffusion)技術,允許使用者透過即時輸入來引導和改變影片生成內容。這項技術展示了「世界模型(World Models)」在未來遊戲開發、虛擬環境模擬與即時互動生成藝術中的巨大潛力。
Google announced new generative media models and tools at I/O 2025, led by Veo 3 for video, Imagen 4 for images, and Flow for AI filmmaking. Veo 3 adds audio generation, while Imagen 4 improves detail, typography, aspect ratios, and up to 2K output. Google also expanded Lyria 2 and Lyria RealTime access, while continuing SynthID watermarking and launching SynthID Detector.