R²D²: Boost Robot Training with World Foundation ... - NVIDIA Developer
Aug 8, 2025 · DiffusionRenderer is a neural rendering framework that enables photorealistic relighting, material editing, and object insertion from a single video input without requiring explicit 3D geometry …
Develop Custom Physical AI Foundation Models with NVIDIA Cosmos …
Jun 11, 2025 · The DiffusionRenderer method, integrated into Cosmos to combine high-quality synthetic data and real-world video to improve lighting realism, geometry, and material accuracy in long video …
Accelerating Diffusion Models with an Open, Plug-and-Play Offering
Jan 27, 2026 · This blog introduces NVIDIA FastGen, an open source library that unifies state-of-the-art diffusion distillation techniques for accelerating many-step diffusion models into one-step or few-step …
Search | NVIDIA Developer
NVIDIA Research has developed DiffusionRenderer, an AI-powered rendering technique that can transform lighting in videos, turning daytime scenes into nightscapes and adjusting lighting conditions.
Optimizing Transformer-Based Diffusion Models for Video Generation …
Apr 21, 2025 · Optimizing Transformer-Based Diffusion Models for Video Generation with NVIDIA TensorRT Apr 21, 2025 By Maximilian Müller, Sagar Singh, Abhinav Sharma, Allie Yang and Allen …
Understanding Diffusion Models: An Essential Guide for AEC ...
Jul 10, 2024 · Diffusion models, a key component of generative AI, can generate high-quality data from prompts by progressively adding and removing noise from a dataset, and are being used in the …
Double PyTorch Inference Speed for Diffusion Models Using Torch ...
Jul 24, 2025 · While this blog post features FLUX, this workflow generalizes to many diffusion models supported by HuggingFace Diffusers, such as Stable Diffusion and Kandinsky. Learn more and view …
Rethinking How to Train Diffusion Models | NVIDIA Technical Blog
Mar 21, 2024 · After exploring the fundamentals of diffusion model sampling, parameterization, and training as explained in Generative AI Research Spotlight: Demystifying Diffusion-Based Models…
NVIDIA TensorRT Accelerates Stable Diffusion Nearly 2x Faster with 8 ...
Mar 7, 2024 · NVIDIA TensorRT's 8-bit quantization technique achieves up to 1.95x speedup in Stable Diffusion XL inference on NVIDIA RTX 6000 Ada GPUs while preserving image quality. The …
Tag: Diffusion models | NVIDIA Technical Blog
Oct 31, 2023 · Advancing Anomaly Detection for Industry Applications with NVIDIA NV-Tesseract-AD In a recent blog post, we introduced NVIDIA NV-Tesseract, a family of models designed to unify …