Global radar

🗣️ PersonaPlex - NVIDIA's real-time speech-to-speech conversational AI model. Natural full-duplex conversations with customizable personas and voices.

Unified multi-harness mission control with 9router-first onboarding, streaming chat, and shared workspace.

Browse, preview and compare Wan2GP / WanGP video generations side by side, with the embedded generation settings and a diff of what changed between runs.

MuScriptor is a multi-instrument music transcription model developed by Kyutai and Mirelo.

AI filmmaking on a node canvas. Generate locally on your own GPU with the Inline Core engine (Z-Image, Krea 2, FLUX.2, MiniMax H3), or use hosted models with no GPU. Train your own LoRAs locally on the same canvas. Every render is kept as a versioned take, so you never lose the good version. Free and open source.

Founder-controlled real-estate lead operations with seven local agents, consented lead records, authenticated Google Ads keyword reads, and review-only campaign exports.

Video inpainting (object removal / video completion) - sczhou/ProPainter

Geostatistical utilities and tutorial in R. For the tutorials I have included Rmarkdown html files.

Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server (https://github.com/radames/Real-Time-Latent-Consistency-Model)

A Real-Time Text-to-Image Generation Model

Simulate Before Reality.

Upload MP3 files, split into chunks, and transcribe to text using Whisper.

A Web UI for easy subtitle using whisper model.

[NVIDIA ONLY] Temporally Consistent Human Image Animation using Diffusion Model https://showlab.github.io/magicanimate/

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Transform your ideas into high-quality video content with the Unlimited AI 18+ Video Generator. Tailored for adult content creators and digital artists, this advanced software offers powerful rendering tools and intuitive controls to turn prompts and images into fluid, realistic video sequences.

state-of-the-art tuning-free method to achieve ID-Preserving generation with only single image, supporting various downstream tasks. https://instantid.github.io/

Customizing Realistic Human Photos via Stacked ID Embedding https://huggingface.co/spaces/TencentARC/PhotoMaker-V2