Swap faces in photos and videos in seconds — no training required. Powered by InsightFace and ONNX, with optional TensorRT acceleration, multi-face targeting, enhancement pipelines, and a clean one-click interface.
mikecastrodemaria/Fooocus2026-pinokiov3.6updated 2mo ago
A personal fork of lllyasviel/Fooocus v2.5.5 with quality-of-life features: Save Preset, CivitAI Model Settings, LoRA trigger words, Embeddings panel, Wildcards editor, Vary-with-aspect-ratio, Custom Resolution, Asset Browser, Restart UI button.
Dub & translate any short video — locally, offline. Voice clone / per-speaker cast / voice packs, on-screen text localized in place, subtitle styling, blur-or-solid mask covers, funny re-dub. One process (FastAPI serves the React SPA), 6 UI languages.
MuseTalk is a cutting-edge video-to-video (V2V) lip-sync solution engineered to deliver highly accurate and natural mouth movements synchronized to audio input. Precision LipSync: Realistic and seamless synchronization of speech audio to facial movements. Efficiently designed to run on 8–12 GB VRAM,
pinokiofactory/Orpheus-TTS-FastAPIv3.7updated 2mo ago
Orpheus TTS is an open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis https://github.com/canopyai/Orpheus-TTS
P2PCLAW Agent Benchmark — connect any LLM agent (Claude, GPT, Gemini, Qwen, Kimi, DeepSeek…) and get scored on 10 dimensions + Tribunal IQ. Dashboard runs locally on :8787, leaderboard at p2pclaw.com/app/benchmark.
Diffusion Engine for Musical Orchestrated Noise — a real-time streaming diffusion engine for music generation, built on ACE-Step v1.5. Requires an NVIDIA GPU.
b2renger/magenta-rt-pinokio-windowsv7.0updated 2mo ago
[Windows · NVIDIA · WSL2] Google Magenta's real-time music generation model with a FastAPI/Gradio web UI. The JAX/CUDA stack runs inside a dedicated, isolated WSL2 distro.