slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It provides a clean, ComfyUI-native integration of a powerful one-step restoration and upscaling model, with automatic verified downloads and no external dependencies beyond ComfyUI.
Who it is for
- ComfyUI users seeking high-quality image restoration
- Digital artists and photographers needing upscaling and denoising
- AI enthusiasts wanting an easy way to run SeedVR2
- Batch image processors looking for reliable ComfyUI nodes
Use cases
- Restoring old or damaged photos (denoise, deblur, sharpen)
- Upscaling low-resolution images up to 8x
- Enhancing detail in digital artwork
- Batch processing multiple images with alpha channel preservation
Strengths
- Native ComfyUI execution using built-in model paths and memory management
- Automatic resume-enabled downloads with SHA-256 and size validation
- Supports RGBA alpha channel and independent batch processing
- Lightweight – no second implementation or import-time patching
Considerations
- Requires ComfyUI 0.28.0+ with native SeedVR2 support
- Model download size ~3.4 GB, network access needed on first use
- Only MPS fully tested; CUDA, ROCm, and CPU not verified for this release
README quick start
Installation
Description
SeedVR2 1.4B image restoration and upscaling nodes for ComfyUI
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.