AI-generated illustration, not actual output from this listing
What they did
A front-end for VapourSynth focused on video upscaling.
Worth knowing
Price: Open source (GPL-3.0)
License: GPL-3.0
Status: sourced. We have not run this ourselves yet (no "Tested" badge).
Quality bar (computed by code): 4/5 (primary source ✓, reproducible ✗, new ✓, example output ✓, safe ✓)
Get Atlas Dispatch
The best new AI video workflows and prompts, weekly.
Weekly: 5 new prompts and workflows. Unsubscribe anytime.
From the source
Setup. Free desktop app for Windows (installer or archive; click 'Start Setup' on first launch) and Linux (AppImage that uses your distro's Python, FFmpeg and Vulkan driver). First-run setup installs VapourSynth, plugins and models into a private environment without sudo. GPL-3.0.
Inputs. Drag in a video, choose an upscaling model, set the output location and format, then click Upscale Video. Backends: TensorRT (NVIDIA), DirectML (Windows), NCNN Vulkan and MIGraphX (AMD). Import your own ONNX models, chain custom VapourSynth filters, and save .vkfilter and .vkworkflow presets for batch runs.
What the source says about results. It has a real-time preview while processing and a built-in side-by-side compare viewer for checking output against the source. The README publishes no quality benchmarks.
Connect Claude, ChatGPT, Cursor, Gemini or Grok Bot to Atlas, and your agent can plan shots, pick models and price them from the data on this site. Free. No sign-up or API key.
