An auditable migration assistant for AI projects that need to run without an NVIDIA CUDA dependency. It retains the existing CUDA-to-HIP converter and adds a standalone project scanner and runtime planner for ROCm/HIP, DirectML, ONNX Runtime DirectML, MIGraphX, and CPU fallback
AI video generation browser for Wan2GP / WanGP: local library, full generation recipe per clip (seed, steps, LoRAs, prompt), settings diff and side-by-side / wipe / blink A/B comparison. Also browses ComfyUI output folders. 1-click Pinokio install, zero dependencies.
Pinokio launcher for the bounty hunter: an agent that reads a public support board, answers with the model you already run, and earns USDC when a human approves it.
Pinokio launcher for Fish Audio Drama 3: full model with MoE expert offload on 24+ GB NVIDIA GPUs, drama3-small on 16 GB, MLX on Apple Silicon
To associate your repository with the pinokio-script topic, visit your repo's landing page and select "manage topics."