NVIDIA unlocks even more 3D Generative AI at GTC

AT GTC, NVIDIA Edify, a multimodal architecture for visual generative AI, has been shown with expanded capabilities. As part of CEO Jensen Huang’s extensive 2-hour keynote, a host of new tools were briefly touched on, and many will become increasingly important to VFX teams.
在 GTC 上，NVIDIA Edify（一种用于视觉生成式 AI 的多模态架构）已展示具有扩展功能。在首席执行官黄仁勋（Jensen Huang）长达2小时的主题演讲中，简要介绍了许多新工具，其中许多工具对视觉特效团队来说将变得越来越重要。

3D asset generation is among the latest capabilities Edify offers developers and visual content providers. With new generation tools, users can exert more creative control over their AI image generation. For example, Shutterstock is rolling out early access to an API built on the latest Edify architecture that lets creators rapidly use text prompts or images to generate 3D objects for virtual scenes.
3D 资产生成是 Edify 为开发人员和视觉内容提供商提供的最新功能之一。借助新一代工具，用户可以对他们的 AI 图像生成进行更具创造性的控制。例如，Shutterstock 正在推出对基于最新 Edify 架构构建的 API 的抢先体验，该 API 允许创作者快速使用文本提示或图像为虚拟场景生成 3D 对象。

Visual content creator Getty Images will now add custom fine-tuning capabilities to its commercially safe Generative AI service, helping enterprise customers generate visuals that adhere to brand guidelines and styles.
视觉内容创建者Getty Images现在将为其商业安全的生成式AI服务添加自定义微调功能，帮助企业客户生成符合品牌准则和风格的视觉效果。

Developers can soon test drive pre-trained Edify models by Getty Images and Shutterstock as APIs through NVIDIA NIM, a collection of microservices for inference announced today at the keynote. Developers can also train and deploy their own generative AI models using the Edify architecture through NVIDIA Picasso, an AI foundry built on NVIDIA DGX Cloud.
开发人员很快可以通过 NVIDIA NIM 将 Getty Images 和 Shutterstock 的预训练 Edify 模型作为 API 进行测试，NVIDIA NIM 是今天在主题演讲中宣布的用于推理的微服务集合。开发人员还可以通过基于 NVIDIA DGX Cloud 构建的 AI 代工厂 NVIDIA Picasso 使用 Edify 架构训练和部署自己的生成式 AI 模型。

Livestreaming platform Be.Live is using the NVIDIA Picasso foundry service to provide real-time generative AI that enables the automated creation of visuals and an interactive experience for audiences. Bria, a holistic platform tailored for businesses developing responsible visual generative AI, has adopted Picasso to run inference. And creative studio Cuebric is enhancing filmmaking and content creation by developing Picasso-powered generative AI applications to build immersive virtual environments.
直播平台 Be.Live 正在使用 NVIDIA Picasso foundry 服务来提供实时生成式 AI，从而能够自动创建视觉效果并为观众提供交互式体验。Bria 是一个为开发负责任的视觉生成式 AI 的企业量身定制的整体平台，它采用了 Picasso 来运行推理。创意工作室 Cuebric 正在通过开发毕加索驱动的生成式 AI 应用程序来构建身临其境的虚拟环境，从而增强电影制作和内容创作。

Shutterstock’s 3D AI Services, available in early access, will enable creators to generate virtual objects for set dressing and ideation. This capability can drastically reduce the time needed to prototype a scene, giving artists more time to focus on hero characters and objects.
Shutterstock 的 3D AI 服务现已推出抢先体验版，它将使创作者能够生成用于布景和构思的虚拟对象。此功能可以大大减少制作场景原型所需的时间，让艺术家有更多时间专注于英雄角色和对象。

The commercially safe model was trained on Shutterstock’s licensed data. Shutterstock has actually compensated hundreds of thousands of artists, with anticipated payments to millions more, for their content IP’s role in training generative technology.
商业安全模型是在 Shutterstock 的许可数据上训练的。Shutterstock 实际上已经补偿了数十万艺术家，预计还会向数百万人支付费用，因为他们的内容 IP 在培训生成技术方面发挥了作用。

Using the tools, creative professionals will be able to rapidly create assets from text prompts or reference images and choose from a selection of popular 3D formats to export their files. The Edify 3D based service will also come with built-in safeguards to filter generated content.
使用这些工具，创意专业人士将能够从文本提示或参考图像中快速创建资产，并从一系列流行的 3D 格式中进行选择以导出他们的文件。基于 Edify 3D 的服务还将带有内置的保护措施来过滤生成的内容。

Product visualization rendering
产品可视化渲染

Getty Images 盖蒂图片社

Getty Images continues to expand the capabilities offered through its commercially safe
Getty Images 继续扩展其商业安全功能
generative AI service, which provides users with indemnification for the content they generate.
生成式 AI 服务，为用户提供对他们生成的内容的赔偿。

The Getty Images AI is trained exclusively on Getty Images’ own creative content. As such, the new images created are commercially safe—trained exclusively on permission-approved data to prevent problematic imagery generation.
Getty Images AI 专门针对 Getty Images 自己的创意内容进行训练。因此，创建的新图像在商业上是安全的——专门使用许可批准的数据进行训练，以防止生成有问题的图像。

New Edit tools 新的编辑工具

Getty Images released Edify-powered APIs for inpainting, to add, remove or replace objects in an image, and outpainting, to expand the creative canvas. These new features are now available on both Gettyimages.com and iStock.com and starting in May, Getty Images will also offer services to custom fine-tune the Edify foundation model to a company’s own brand and visual style.
Getty Images 发布了由 Edify 提供支持的 API，用于修复，用于添加、删除或替换图像中的对象，以及用于扩展创意画布的外部修复。这些新功能现已在 Gettyimages.com 和 iStock.com 上提供，从5月开始，Getty Images还将提供服务，根据公司自己的品牌和视觉风格定制微调Edify基金会模型。

The new services will feature a no-code, self-service method for companies to upload a proprietary dataset, review automatically generated tags, submit fine-tuning tasks and review the results before deploying to production.
新服务将采用无代码的自助服务方法，让公司上传专有数据集、审查自动生成的标签、提交微调任务并在部署到生产环境之前审查结果。

As part of custom fine-tuning tools, Getty Images will release a collection of APIs that provide finer control over image output, one of the biggest challenges in generative AI. Developers will soon be able to access Sketch, Depth, and Segmentation features — which allow users to provide a sketch to guide the AI’s image generation, copy the composition of a reference image via a depth map, and segment parts of an image to add, remove or retouch a character or object. Users can download and license any visual they generate, at the user’s desired resolution.
作为自定义微调工具的一部分，Getty Images 将发布一系列 API，以提供对图像输出的更精细控制，这是生成式 AI 面临的最大挑战之一。开发人员很快将能够访问草图、深度和分割功能，这些功能允许用户提供草图来指导 AI 的图像生成，通过深度图复制参考图像的构图，以及分割图像的某些部分以添加、删除或修饰角色或对象。用户可以下载并许可他们生成的任何视觉对象，并按用户所需的分辨率进行许可。

360 AI HDIs 360 度 AI HDI

Dassault Systèmes’ 3DEXCITE applications for 3D content creation and CGI studio Katana are incorporating Shutterstock generative 360 HDRi APIs into their workflows based on NVIDIA Omniverse, a computing platform for developing OpenUSD-based 3D workflows and applications.
达索系统用于 3D 内容创作的 3DEXCITE 应用程序和 CGI 工作室 Katana 正在将 Shutterstock 生成式 360 度 HDRi API 整合到其基于 NVIDIA Omniverse 的工作流程中，NVIDIA Omniverse 是一个用于开发基于 OpenUSD 的 3D 工作流程和应用程序的计算平台。

Shutterstock is also building Edify-based tools to light 3D scenes using 360 HDRi environments generated from text or image prompts.
Shutterstock 还在构建基于 Edify 的工具，以使用从文本或图像提示生成的 360 度 HDRi 环境来照亮 3D 场景。

Conversation Prompts to 3D environment
对话提示到 3D 环境

Accenture Song is using the Omniverse platform to generate high-fidelity Defender vehicles from computer-aided design data for marketing purposes. Coupled with generative AI microservices  Accenture Song is enabling the creation of cinematic, interactive 3D environments via conversational prompts. The result is a fully immersive 3D scene that couples realistic generated environments with a digital twin of the Defender vehicle. The NVIDIA Text to image prompt tools are currently available in 75 languages.
Accenture Song 正在使用 Omniverse 平台从计算机辅助设计数据中生成高保真 Defender 车辆，用于营销目的。结合生成式 AI 微服务，Accenture Song 支持通过对话提示创建电影般的交互式 3D 环境。其结果是一个完全身临其境的 3D 场景，将逼真的生成环境与 Defender 车辆的数字孪生相结合。NVIDIA 文本到图像提示工具目前提供 75 种语言版本。

 

Clients 客户

Getty Images’ API services are already being used by leading creatives and advertisers including:
Getty Images 的 API 服务已被领先的创意人员和广告商使用，包括：
● Dentsu Inc.: The Japan-based ad agency is using Getty Images’ generative AI API service to power MAFA: Manga Anime For All, an app that can create manga and anime-style content for marketing use cases.
● Dentsu Inc.：这家总部位于日本的广告公司正在使用 Getty Images 的生成式 AI API 服务来支持 MAFA： Manga Anime For All，这是一款可以为营销用例创建漫画和动漫风格内容的应用程序。
● McCann: The creative agency harnessed generative AI to help develop an innovative game for its client Reckitt’s over-the-counter cold medicine Mucinex, in which customers can interact with the brand’s mascot.
● 麦肯（McCann）：这家创意机构利用生成式人工智能帮助其客户利洁时（Reckitt）的非处方感冒药Mucinex开发一款创新游戏，客户可以在其中与该品牌的吉祥物互动。
● Refik Anadol Studio: Known for using generative AI in its artwork, the studio is showcasing a rainforest-inspired art installation at GTC, created using Getty Images’ AI model fine-tuned with Refik’s rainforest catalog.
● Refik Anadol Studio：该工作室以其艺术作品中使用生成式 AI 而闻名，该工作室正在 GTC 上展示一个以热带雨林为灵感的艺术装置，该装置使用 Getty Images 的 AI 模型创建，该模型与 Refik 的热带雨林目录进行了微调。
● WPP: The marketing and communications services company is partnering with The Coca-Cola Company to explore how fine-tuning Getty Images’ model can help to build custom visuals that meet brand styles and guidelines.
● WPP：这家营销和传播服务公司正在与可口可乐公司合作，探索如何微调Getty Images的模型，以帮助构建符合品牌风格和准则的自定义视觉效果。