- Home
- Image Upscaling Software
- VisionSR
On the recordRead 12 Oct 202626 facts
VisionSR
On the record
- API
- The HTTP API includes image analysis, enhancement jobs, live progress events over SSE, and job results.github.com · read 12 Oct 2026
- API access
- Yesgithub.com · read 22 Sep 2026
- Automatic routing
- It analyzes image content and damage, then automatically selects a suitable model and tile size based on available VRAM.github.com · read 12 Oct 2026
- Batch processing
- Yesgithub.com · read 22 Sep 2026
- Desktop app
- Yesgithub.com · read 22 Sep 2026
- Desktop features
- The desktop app includes a watched hot folder and native open and save, and starts its own engine process.github.com · read 12 Oct 2026
- Hardware
- The README describes tiled inference designed for a 4 GB GPU; GPU installation requires an NVIDIA card, while the packaged ONNX Runtime and DirectML app is described as supporting DX12 GPUs from NVIDIA, AMD, or Intel.github.com · read 12 Oct 2026
- Hardware requirements
- The project requires Python 3.11 or later, and an NVIDIA card for GPU use; tiled inference is designed to work from 4 GB VRAM.github.com · read 12 Oct 2026
- Image tools
- Listed capabilities include super resolution, face restoration, and background removal.github.com · read 12 Oct 2026
- Image workflows
- Features include batch folder processing, face restoration, background removal, image analysis, and model inspection.github.com · read 12 Oct 2026
- Integrations
- The README documents PyTorch, ONNX Runtime, DirectML, and OpenVINO as supported inference backends.github.com · read 12 Oct 2026
- Intended users
- The project describes a 4 GB laptop GPU as its design target and includes model paths for photographs, portraits, scans, and line art.github.com · read 12 Oct 2026
- Interfaces
- It provides a CLI, Python interface, HTTP API, web UI, and Electron desktop app.github.com · read 12 Oct 2026
- License
- The project is licensed under Apache-2.0, and the README says model weights have their own licenses and are downloaded rather than redistributed.github.com · read 12 Oct 2026
- Limits
- The README says the training pipeline and cloud or multi-tenant layer are not built.github.com · read 12 Oct 2026
- Local processing
- The project says images are processed locally, with no upload, per-image cost, or queue.github.com · read 12 Oct 2026
- Maximum scale
- 4xgithub.com · read 22 Sep 2026
- Models
- The README lists nine models for super resolution, anime and illustration upscaling, face restoration, background removal, and face detection.github.com · read 12 Oct 2026
