Creative GenerationVerified
Reviewed and published by trentmaziarz, April 21, 2026. Discovered and drafted by our automated research pipeline.
NVIDIA deployed DLSS (Deep Learning Super Sampling), a suite of AI technologies built into GeForce RTX GPUs that generates additional video game frames and upscales images in real time to boost visual performance. As of January 2025, over 540 games and applications support DLSS; as of January 2026, over 250 of those support Multi Frame Generation, the latest frame-generation feature.
Details
DLSS uses neural networks trained on NVIDIA's supercomputers to take lower-resolution rendered frames and game motion data as input, then output higher-quality, higher-framerate images in real time. DLSS 4, launched in January 2025 alongside the GeForce RTX 50 Series, introduced Multi Frame Generation using transformer-based AI models; on RTX 50 Series GPUs it can generate up to three additional frames per natively rendered frame (a 4X multiplier). DLSS 4.5, launched at CES 2026, introduced a second-generation transformer model for Super Resolution and a 6X Multi Frame Generation mode that generates up to five additional frames per natively rendered frame, as well as Dynamic Multi Frame Generation, which adjusts the frame multiplier automatically to match a target frame rate.
Products affected
NVIDIA DLSSGeForce RTX GPUsNVIDIA App
Sources & Evidence
News Article
Company Disclosure
Cite this record
Trace Foundation. (2026). NVIDIA: NVIDIA deployed DLSS (Deep Learning Super Sampling), a suite of AI technologies built into GeForce RTX GPUs that generates additional video game frames and upscales images in real time to boost visual performance. As of January 2025, over 540 games and applications support DLSS; as of January 2026, over 250 of those support Multi Frame Generation, the latest frame-generation feature (data as of 2026-04-27) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/f959bf1d-9fde-4bb0-addf-47ec40c3cf73. Accessed September 7, 2026.
- Stable link
- https://www.aitrace.org/r/practice/f959bf1d-9fde-4bb0-addf-47ec40c3cf73
- Data as of
- April 27, 2026
- Last verified
- April 21, 2026
Other practices by NVIDIA
Data AnalysisNVIDIA offers Morpheus, an open-source AI cybersecurity framework that allows enterprises and security vendors to build real-time pipelines for detecting threats such as anomalous user behavior, spear phishing emails, and sensitive data leakage across data center networks. Best Buy's CISO cited the framework as a foundation for ML-based anomaly detection at the April 2021 launch; Booz Allen Hamilton has built a product called Cyber Precog on top of Morpheus for use by its own customers.ProductivityNVIDIA offers NIM (NVIDIA Inference Microservices), a set of prepackaged AI model containers that let developers and enterprises deploy large language models and other AI models in minutes rather than weeks, across clouds, data centers, and local workstations. NIM became generally available to developers in June 2024.Creative GenNVIDIA offers Picasso, a cloud service that lets businesses build applications capable of generating images, videos, and 3D objects from text prompts using NVIDIA's Edify foundation models. Enterprise customers including Getty Images, Shutterstock, and Adobe have integrated these tools into their own creative platforms.
Have evidence about NVIDIA's AI practices? Submit a report.
Report a Sighting →