By Zak Killian
Publication Date: 2026-09-24 14:00:00
NVIDIA just published a new developer-focused blog post detailing how game makers can control DLSS 5’s 3D-guided neural rendering, and while most of the information in the post will be familiar to anyone who has been following DLSS 5 closely (and, indeed, to anyone who read our launch coverage) it offers a useful look at why NVIDIA gives developers so many knobs to control the technology in the first place.
As we covered ahead of launch, developers can select from multiple DLSS 5 models, adjust Structure Intensity and Tone Intensity, and use both semantic AI masking as well as engine-level masks to control where the effect is applied. DLSS 5 can also make use of richer input data such as ray-traced or path-traced lighting, which NVIDIA says produces substantially more accurate results. The one particularly interesting new tidbit in this latest developer post is that Visual Concepts apparently uses a per-pixel uplift control mask in NBA 2K27 to fine-tune character detail while preserving player likenesses.
Those controls are particularly important in light of the DLSS 5 modding scene that emerged almost immediately after NBA 2K27 released. Before DLSS 5 even launched, modders extracted NVIDIA’s nvngx_dlssnr.dll from the game and figured out how to inject the neural-rendering model into other titles,…
