DLSS 5 ships: one-step pixel diffusion generates photorealistic 4K frames in real time
ctnzr · x · 2026-09-04
DLSS 5 is officially out: the first DLSS with a generative stage, using a real-time, 3D-guided one-step pixel-space diffusion model to turn rendered frames into photorealistic 4K scenes while preserving developer-authored content. The team explains why generation is needed — VRAM and compute cap both scene abstraction and ray counts, so even perfect reconstruction was bounded; DLSS 5 generates beyond that ceiling while staying grounded in the game and artist-controlled. Compared with offline models like GPT Image 2 and Gemini 3 Pro, it matches realism with far more faithful preservation of identity and scene structure. A technical report covers comparisons with offline generative models at similar scaling cost.
More from Multimodal
- Lyria 3.5 arrives in Gemini: templates, vocal/instrumental choice, longer tracks — GeminiApp · 2026-09-05
- Google ships Lyria 3.5 music model in Gemini with richer vocals and arrangements — GeminiApp · 2026-09-05
- Fei-Fei Li's World Labs unveils Atlas world model: 3 photos replace 300 for 3D capture — theworldlabs · 2026-09-05
- Seedance 2.5 workflow: real product photo + identity sheet generate 24s UGC testimonial ads — socialwithaayan · 2026-09-05
- GPT Image 2 turns one selfie into a six-panel turnaround sheet for AI ad videos — socialwithaayan · 2026-09-05
- GPT Image 2 turnaround sheets + Seedance 2.5: a reproducible AI UGC ad workflow — socialwithaayan · 2026-09-05