- 4x video upscaling with temporal coherence using Stream-DiffVSR - Model Loader node with precision/device options and xformers support - Upscaler node with chunked processing for memory efficiency - Automatic model download from HuggingFace - Text-guided upscaling support 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>