At SIGGRAPH, NVIDIA Advances Graphics and Simulation With Agentic and Physical AI

At this year’s SIGGRAPH conference, running through Thursday, July 23, in Los Angeles, attendees can discover how leading graphics research, neural rendering, simulation and AI are transforming how worlds are created and understood by people and machines.

The NVIDIA keynote, taking place today, July 20, at 3:45 p.m. PT, will feature NVIDIA AI research and engineering leaders Neil Ashton, Edward Liu and Ming-Yu Liu discussing neural rendering techniques, world models and simulation methods for AI, built by AI.

Read on for the latest from the SIGGRAPH conference, with NVIDIA and partners showcasing:

- Model Context Protocol connections bring agentic AI to content creation

- New Synthetic Video Detector NIM microservice

- Cosmos 3 Edge open world model for local physical AI

- NVIDIA NemoClaw on DGX Station with NVIDIA Agent Toolkit

- Research breakthroughs for virtual worlds and physical AI

AI Agents Expand Creative Tools to Millions 🔗

Leading creative applications are opening Model Context Protocol (MCP) connections that let AI agents work inside the tools where scenes, shots, timelines, assets and edits come to life — while creators stay in control.

For more than two decades, NVIDIA technologies — from GPU-accelerated viewports and CUDA-powered effects to NVIDIA RTX PRO ray tracing, AI denoising, neural rendering and real-time simulation — have helped accelerate the DCC tools that artists, studios and developers use to build the world’s games, films, television shows and advertising content.

MCP is opening the next chapter of accelerated creativity: applications aren’t just getting faster. They’re becoming agent-ready.

From Acceleration to Action

With MCP-connected tools, an artist or technical director can ask an agent to inspect a scene for missing textures, flag inconsistent color management, prepare export variants, generate playblasts for dailies or validate a shot against pipeline rules, all while keeping creative decisions in human hands.

The same NVIDIA platform that accelerated viewports, rendering, simulation and AI effects can now power local agents, model inference and multi-application workflows on systems designed for professional creators.

NVIDIA RTX PRO workstations, DGX Spark and DGX Station systems are designed to bring accelerated AI performance closer to artists, developers and studio pipelines. Running models and agents locally can help improve responsiveness, reduce reliance on external services and keep sensitive creative data in controlled environments.

NVIDIA Agent Toolkit also supports MCP integration, including an MCP client for connecting to remote MCP servers and an MCP server for publishing tools to any MCP client.

The Creative Ecosystem Goes Agent-Ready

Across the creative ecosystem, creative applications and platforms are exposing MCP connections or MCP-ready workflows, giving AI agents more grounded access to real production context.

Adobe is expanding its creative agent across Firefly, Express and Creative Cloud, powering AI Assistant experiences that enable creators to describe the outcome they want while the assistant orchestrates multistep workflows. Adobe is also bringing its pro-grade creative tools to third-party AI platforms through the Adobe connector, extending its creative capabilities wherever people create and work. For developers, Adobe provides the Adobe Express Developer MCP Server, enabling AI coding assistants to build Adobe Express add-ons using official documentation and application programming interfaces (APIs).

Affinity by Canva has introduced an AI Connector for Claude that uses MCP to bring natural-language automation directly into Affinity. Designers can ask Claude to handle repetitive production tasks such as renaming layers and artboards, resizing and reformatting assets for multiple channels, applying bulk edits, optimizing vector paths and preparing files for delivery. Beyond individual tasks, Claude can also help users build reusable scripts and custom features tailored to their workflows, reducing production overhead and giving creative professionals more time to focus on design.

Blender offers a lightweight MCP server through Blender Lab, providing a natural-language interface to Blender’s Python API, documentation and complex setups. For independent artists and studios, Blender offers a strong example of how open creative tools can become agent-accessible without changing the creative center of gravity.

Boris FX Silhouette now includes an MCP server that lets AI assistants work directly inside your projects. Using Silhouette’s FX Scripting API as first-class MCP tools, assistants can inspect projects, build node trees, edit shapes and keyframes, and render frames. A new preferences panel simplifies setup by installing the MCP package, generating a ready-to-paste client configuration, and testing the connection. Interactive online mode connects to your active session, while offline mode runs headless instances for automation, batch processing, and large-scale workflows.

Foundry Griptape natively supports MCP, providing AI orchestration specifically designed for professional VFX pipelines. This integration enables studios to securely manage multiple AI models and agents while maintaining the necessary traceability and creative control. By integrating with tools like Blender and Foundry Nuke, Griptape automates repetitive production tasks — such as cleanup, matte painting and quality control — all while ensuring artists remain in final command of the creative process.

SideFX is bringing MCP support to Houdini 22 through its new APEX Script workflow. AI assistants can access a curated collection of APEX Script syntax, functions, documentation and examples, helping artists generate and refine code for procedural character rigs. SideFX’s initial implementation focuses on APEX Script and character rigging, while community-developed MCP servers offer broader ways for agents to interact with Houdini.

Unreal Engine recently announced the ability to connect AI clients to Unreal Editor through MCP, enabling AI workflows that can interact with editor capabilities through a standardized protocol. For game developers, virtual production teams and real-time artists, this opens the door to assistants that can reason over scenes, assets and project state.

See how NVIDIA RTX PRO and DGX systems bring local AI agents closer to creative work at SIGGRAPH.

NVIDIA AI for Media Helps Newsrooms Detect Synthetic Video 🔗

Every day, video brings the world’s biggest stories into view — from breaking news across continents, to events reshaping communities, to moments that unite people across the globe. In a news cycle that moves around the clock, trustworthy video is the medium through which people see what’s happening, understand why it matters and stay connected and up to date.

For that reason, public trust in video is more essential than ever. At SIGGRAPH, NVIDIA announced the Synthetic Video Detector NVIDIA NIM microservice, part of the NVIDIA AI for Media platform, to bring an AI-assisted detection signal into editorial and media workflows.

The NIM microservice analyzes video frame by frame to produce a classifier score of whether it contains synthetic content. Editorial teams can use that score to prioritize clips for review, flag or quarantine questionable footage, or escalate it for deeper analysis.

Rather than replacing established verification practices, the microservice provides another signal for time-sensitive decisions — helping teams move quickly while protecting editorial standards and ensuring public trust.

Synthetic Video Detector remains effective after the compression, resizing, cropping and re-encoding steps common in newsroom and social-video workflows. In NVIDIA testing, the model’s accuracy reached up to 92% on uncompressed video, 87% at 15% compression and 82% at 50% compression.

The NIM microservice can process 1080p video in as little as 22 milliseconds on NVIDIA RTX systems and approximately 30 milliseconds on NVIDIA L40 GPUs.

Deploy Detection Where Video Lives

Organizations can deploy the NIM microservice closer to where sensitive video is captured, stored or distributed, including in on-premises, edge, hybrid and approved air-gapped environments. This flexibility helps teams maintain control over video data, access and operations.

Partner adoption is already helping move Synthetic Video Detector from model capability to deployable media infrastructure. Wowza is embedding the microservice through the Wowza Video Intelligence Framework, bringing real-time synthetic video detection into livestreaming workflows used across more than 35,000 deployments in over 170 countries.

That scale matters because many of the organizations most exposed to synthetic media risk, including broadcasters, government agencies, financial institutions and critical infrastructure operators, also face strict requirements around data residency, security and operational control.

By pairing Synthetic Video Detector with a video infrastructure layer customers already use, Wowza can help make AI-assisted verification available closer to ingest and streaming operations, allowing teams to flag questionable video in real time while keeping sensitive footage inside their own environments.

Try the NVIDIA Synthetic Video Detector NIM microservice.