Google 全新「任意對任意」AI 模型 Gemini Omni 實測：效果驚人且近乎無縫★ 85
The Verge AI22 days agoReleaseGoogle recently unveiled a brand-new "anything-to-anything" multimodal AI model — Gemini Omni — whose powerful cross-modal generation and transformation…
Google I/O 2026 重磅發布：Gemini 3.5 Flash、Omni (NanoBanana 影片模型)、Spark 背景 Agent 與 Antigravity 2.0★ 85
Latent Space25 days agoReleaseIn the latest issue of Latent Space AINews, the major announcements from Google I/O 2026 were covered in depth. Google demonstrated its formidable R&D and…
Vercel AI Gateway 正式支援 Seedance 2.0 影片生成模型
Vercel Changelog60 days agoReleaseVercel announced in its Changelog that its AI Gateway now officially supports the new Seedance 2.0 video generation model. This update provides developers with…
Google 發表 Veo 3.1：全新「影片配方」功能，帶來更高一致性與控制力，並支援直式影片★ 80
Google DeepMind Blog152 days agoReleaseGoogle DeepMind announced on January 13, 2026, the launch of the latest version of its video generation model — Veo 3.1. This update is designed to give…
幕後紀實《ANCESTRA》：將 Google Veo 融入實景真人電影創作★ 75
Google DeepMind Blog232 days agoReleaseGoogle DeepMind recently shared the behind-the-scenes production process of the science fiction short film ANCESTRA, created in collaboration with…
Google DeepMind 推出 Veo 3.1：帶來更強大的創意控制與先進影片生成功能★ 80
Google DeepMind Blog234 days agoReleaseGoogle DeepMind has officially released the latest major upgrade to its video generation model — Veo 3.1. This is an update tailored specifically for creators…
開源影片生成模型回歸：Replicate 推出最快、最便宜的 Wan 2.2 模型★ 75
Replicate Blog318 days agoReleaseReplicate has announced official support for the brand-new open-source video generation model Wan 2.2 on its platform, declaring that "open-source video…
如何撰寫 Google Veo 3 提示詞以獲得最佳影片生成效果：Replicate 專家指南★ 75
Replicate Blog369 days agoTutorialGoogle's Veo 3 is one of the most advanced video generation models available today, and it is now accessible on the Replicate platform. To help creators and…
SOTA 影片生成新里程：Google Veo 2 與快手 Kling 2 正式對開發者全面開放 (GA)★ 85
TLDR AI (Buttondown)424 days agoReleaseAI video generation has reached a major milestone: Google's Veo 2 and Kuaishou's Kling 2, currently ranked at the top of the Artificial Analysis Video Arena…
在 Replicate Playground 中輕鬆生成短影片：全新無程式碼影片工作流上線
Replicate Blog513 days agoNew ToolReplicate, a well-known AI open-source model hosting and API services platform, has announced a major update: a new and more convenient short video generation…
AI 影片生成迎來它的「Stable Diffusion 時刻」：開源模型已並肩 OpenAI Sora★ 80
Replicate Blog545 days agoOpinionIn the history of AI development, the open-sourcing of Stable Diffusion in 2022 is regarded as a pivotal turning point in the field of image generation — it…
使用 AnimateDiff 與插幀技術（Interpolator）製作流暢的 AI 生成影片
Replicate Blog984 days agoTutorialThis technical blog post from Replicate introduces a new approach to improving the smoothness of AI-generated video: combining **AnimateDiff** with the…
Runway 攜手 Vercel，以 AI 與高效能前端打造下一代內容創作平台
Vercel Changelog1,220 days agoBusinessAmid the rapid rise of generative AI, Runway — the leading startup renowned for its AI video generation technology (Gen-1, Gen-2) — faced the challenge of…