Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

News stories 9

李飞飞最新世界模型正式开放,我用它一句话造出重庆山城

之前凭借「一张图片生成整个 3D 世界」刷屏的李飞飞世界模型,现在终于向所有人开放了。就在今天,由「AI 教母」李飞飞创办的 World Labs 正式开放世界模型 Atlas,同步上线网页应用和开发者 API,新用户注册即送 10000 积分。体验地址:atlas.worldlabs.ai现在,我们也能亲自体验这项曾经只能在演示视频里看到的能力:随手...

Translation is temporarily offline. Showing the original.
腾讯新闻 · AI频道

MiniMax开源H3-Image:10秒生成16MP图像,价格仅同档工具50%–70%11月10日,MiniMax稀宇科技发布开放权重图像模型MiniMax H3-Image,衍生自H3,支持文生图、图像参考与编辑,10秒内可生成4096×4096、约16MP的4K图像,速度为市面主流5倍。权重已上线Hugging Face,并通过MiniMax开放平台、MiniMax Code与海螺提供服务。其后训练链路强化数据、强化学习、步数压缩、PE与部署优化,兼顾速度与效果。 刚刚 5.2K

MiniMax稀宇科技于11月10日发布并开放权重的图像生成模型H3-Image,可在10秒内生成4096×4096像素、约16MP的4K图像,速度达市面主流水平5倍。该模型支持文本生成图像、图像参考与编辑,最多可使用16张参考图,具备强指令遵循能力与高真实感细节表现。权重已上线Hugging Face,并通过MiniMax开放平台、MiniMax Code与海螺提供服务。官方评测显示其标准模式耗时16.0秒,Highspeed模式10.3秒,显著优于同类模型。定价仅为同档位主流工具的50%-70%,首周生成请求享五折优惠。MiniMax表示将持续开放权重,推动开源模型与闭源模型差距缩小,竞争焦点正转向高分辨率下的效率与成本。

Translation is temporarily offline. Showing the original.
AIBase AI资讯

迪士尼携手Adobe开发专属AI模型,布局主题公园、影视及体育业务迪士尼与Adobe达成多年期战略合作,将共同开发面向迪士尼业务的定制化生成式AI模型,并逐步把AI工具引入主题公园、影视制作和体育媒体等领域,探索内容创作、项目开发与用户互动。合作初期重点加快迪士尼体验部门项目开发,该部门运营全球主题公园、度假区及邮轮业务,双方还将继续利用AI技术推进相关应用。 刚刚 0

迪士尼与Adobe宣布达成多年期战略合作,将共同开发面向迪士尼业务的定制化生成式AI模型,应用于主题公园、影视制作及体育媒体等领域。合作初期重点支持迪士尼体验部门项目开发,并利用AI技术助力华特迪士尼影业StudioLAB的创意探索。Adobe将协助提升ESPN与体育迷的互动,并推动体育档案内容的观众触达。双方基于Adobe Firefly Foundry平台,使用迪士尼IP训练专属私有AI模型,实现内容直接用于实际制作。目前,迪士尼幻想工程已部署定制图像生成模型及手绘草图转概念设计的AI工具。此次合作标志着生成式AI从创意辅助向生产环节延伸,同时强化知识产权控制。

Translation is temporarily offline. Showing the original.
AIBase AI资讯

准确率刷新行业上限,Pangram凭何接连攻克图像与视频AI检测难关?Pangram Labs于11月4日发布Pangram Image1.0图像检测模型及Pangram Image Flash1.0视频检测模型,标志数字内容真伪鉴别迎来更高精度突破。Image1.0利用12种前沿AI图像生成器、基于100张真实图片构建1200张测试集,准确率达99.96%,并能通过热力图精准定位AI生成内容。 刚刚 0

AI实验室Pangram Labs于11月4日发布Pangram Image1.0图像检测模型和Pangram Image Flash1.0视频检测模型。前者基于1200张测试数据,准确率达99.96%,可在低至256×256分辨率下保持96.4%准确度;后者在DF26数据集上准确率达98.7%,领先第二名29个百分点,显著提升数字内容真伪鉴别能力。

Translation is temporarily offline. Showing the original.
AIBase AI资讯

GPT能做动图了!10秒一张,实测“穿帮”有点多

智东西(公众号:zhidxcom)作者 | 陈骏达编辑 | 云鹏OpenAI的图像生成模型,能直出动图了!▲图源:X平台智东西11月5日报道,今天,OpenAI发布新一代图像生成模型Images 2.6。此次升级主打两个方向:一个是生成更快、编辑控制更细,另一个就是首次支持直接生成GIF动图和SVG(矢量图,常用于嵌入网页)导出。按OpenAI给出的...

Translation is temporarily offline. Showing the original.
腾讯新闻 · AI频道

Canva has launched its first in-house image-generation model, Canva Craft, which is now available to all users.

Canva has officially launched its first in-house image-generation model, Canva Craft, which employs a two-stage generative architecture, supports 2K resolution and output in 30 aspect ratios, and emphasizes text readability and layer editability. The model was trained on millions of human-designed templates within the platform and has already been integrated into Dream Lab and the API; going forward, it will be accessible via MCP to third-party chatbots such as ChatGPT and Gemini.

TechCrunch · AI

Canva has launched its in-house AI image-generation model, Canva Craft, which employs a two-stage design and planning architecture.

Canva has launched its first in-house AI image-generation model, Canva Craft, which employs a two-stage architecture—planning followed by generation—to enhance design accuracy, consistency, and controllability. It supports 2K resolution and over 30 aspect ratios, catering to use cases such as social media, marketing content, and digital art.

The Verge · AI

TorchNeuron launches public beta: Hugging Face models natively support AWS Trainium for training and inference.

Hugging Face, in collaboration with AWS, has launched TorchNeuron—a PyTorch-native Trainium backend—available for public beta starting October 20, 2026. This technology enables mainstream libraries such as Transformers and Diffusers to run directly on Trainium chips without any modifications, significantly enhancing the usability and compatibility of text-generation and image-generation models.

Hugging Face Official Blog