Mana

Based on BFS - Best Face Swap, VisoMaster, and SwapAnyHead.

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,

Interpolate, Upscale, Decompress, and Denoise videos Locally on Linux/Windows/MacOS.

Deepfakes Software For All

High quality LipSync Application with a simple UI

Automatically clip videos and generate captions for LoRA training using advanced vision models like Gemma-3, Qwen3-VL, and Qwen2-VL.

Bring portraits to life in Real Time!

i have patched and reengineered open sora to work on windows

Slice any audio file into fixed-length (10-60s) clips and export them all at once. Powered by ffmpeg.

DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

Real-time face animation with FOMM and face-vid2vid engines

Video LoRA studio: NVIDIA CUDA and supported AMD ROCm on Windows/Linux; CPU dataset preparation on Apple Silicon macOS. Models download locally.

An Efficient Framework For High Fidelity Face Swapping

Audit AI projects for CUDA lock-in, plan DirectML/ONNX/ROCm alternatives, and convert source-available CUDA to reviewed HIP drafts.

AI agent that reads real theme-park blueprints, maps and coaster schematics, then builds them automatically in Planet Coaster 1 & 2 via PC-level control (Claude / Gemini / OpenAI vision + PyAutoGUI).