Submit a resource

Navigation

Back to directory

MLX-DLSS

An experimental port of NVIDIA's DLSS neural rendering and frame generation to Apple Silicon using MLX and Metal, plus a PyTorch backend for other GPUs, with a desktop app, web UI and command-line tool.

Visit website (opens in a new tab)github.com
MLX-DLSS

MLX-DLSS runs NVIDIA's DLSS neural rendering and frame generation models on images and video outside NVIDIA hardware. On Apple Silicon it uses MLX and Metal; a PyTorch backend covers other GPUs and CPUs. It is an independent, experimental port, not a game integration or an NVIDIA product, and it requires the user to supply their own NVIDIA libraries to extract the model weights.

Three interfaces share the same engine: a native macOS app built in Swift with a live settings preview, a Python web UI built with NiceGUI, and a command-line tool with a Python API. Temporal rendering using preceding frames is on by default, and an experimental 2x super-resolution mode is also included.

The macOS app needs Apple Silicon, macOS 26 or newer, and a Swift 6.2 toolchain; weight extraction needs Python 3.10 or newer.

More in Generative media

See all 146

  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • ComfyUI-GGUF-Qwen3VL-TE

    github.com

    A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • ComfyUI-QwenImage-PhotoStyles

    github.com

    A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy