Complex

Released PixVerse V4.5 Video Model! Over 20 Movie Lenses + Multi-Image Fusion, Create a Hollywood Blockbuster in 5 Seconds!

PixVerse officially released its V4.5 video model, introducing over 20 new features in cinematic lens control, multi-image reference functionality, and enhanced handling of complex actions (). This update significantly improves the quality and creative freedom of video generation, solidifying PixVerse's leading position in the field of AI video creation. AIbase observed that the release of V4.5 quickly sparked discussions among creators worldwide, being hailed as a "milestone in movie-level AI video creation."Core Features: Professional Lens Control and Multi-Image Fusion.

5/15/2025 10:01:53 AM

AI在线

GPT-4拿下最难数学推理数据集新SOTA，新型Prompting让大模型推理能力狂升

模拟人类推理过程，华为诺亚提出 Progressive-Hint Prompting (PHP) 引导大模型渐近正确答案。

5/14/2023 12:22:00 PM

机器之心

资讯热榜

苹果发布全新Xcode 26开发者工具：内置ChatGPT先进AI功能豆包App“一句话P图”功能全新升级基于SeedEdit 3.0实现全面优化 DeepSeek前高管秘密创业，新AI Agent项目已获顶级VC押注苹果向开发者开放本地AI能力，推出全新Foundation Models框架支持MCP！开源智能体开发框架 Rowboat：打造你的智能助手只需几分钟 Microsoft Releases 700 Real AI Cases to Explore New Intelligent Work Models 苹果将 ChatGPT 和其他 AI 模型引入 Xcode Grok接管推特算法！小号也能爆红，新人起号迎来黄金时代？

标签云

人工智能 AI OpenAI AIGC 模型 ChatGPT DeepSeek AI绘画谷歌数据机器人大模型 Midjourney 用户智能开源微软 GPT Meta 学习图像技术 AI创作 Gemini 论文马斯克 Stable Diffusion 算法英伟达代码 Anthropic 芯片开发者生成式蛋白质腾讯神经网络训练 3D 研究生成智能体苹果计算机器学习 Sora Claude AI设计 AI for Science GPU AI视频人形机器人搜索华为百度场景大语言模型 xAI 预测伟达深度学习 LLM 字节跳动 Transformer Agent 模态具身智能神器推荐工具文本视觉 LLaMA 算力 Copilot 驾驶大型语言模型 API RAG 应用架构