[NVIDIA] Pinokio launcher for the released WorldMirror 2.0 reconstruction app from HY-World 2.0. Uses a cu128 PyTorch baseline with gsplat from PyPI/JIT. https://github.com/Tencent-Hunyuan/HY-World-2.0
Radar
New projects people are discovering or following across Pinokio.
enhance the resolution and spatiotemporal continuity of text-generated videos and image-generated videos
AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]
[NVIDIA ONLY] Generate Video Progressively. FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. https://github.com/lllyasviel/FramePack
YUE2 // GROOVE is the latest music studio built on the open-source Yue2 model and its inference stack. Generate high-quality full songs from style and lyrics with an editable score plan — powered by the latest YuE model — cover from audio with SheetSage2 and MERT2, refine and compare edits, and keep your works in a reusable, easy-to-manage library. You get high-quality creation with real creative control. Hardware: an NVIDIA GPU with 24 GB VRAM on Linux (YuE2's recommended setup, validated end-to-end on NVIDIA L4 hosts; a 16 GB memory budget runs everything the app can produce, and 12 GB runs the unquantized model at CFG 1.0 or for shorter songs) or an Apple Silicon Mac with 32 GB+ unified memory (where this app is developed and tested). Windows is best effort: install, launch, Cover and a full-length song verified on Windows 11 (RTX 2070, 8 GB); song generation there runs through the GGUF engine. Cards under 16 GB (and Windows) get the optional GGUF engine: the same model through yue2.cpp with an 8-bit backbone, 8.2 GB peak for a full song, measured indistinguishable from the reference rendering in a blind ABX, a different take for the same seed; the reference PyTorch configuration stays the default wherever it fits.
The most powerful local music generation model that outperforms most commercial alternatives.
All-in-one Gradio UI for the MOSS-TTS Family: voice cloning, dialogue generation, voice design from text, and sound effects.
1-click MiniMax H3 video in ComfyUI plus H3 Studio: local T2V/I2V, references, continuation, Gallery, Director/Cinema and TR/EN. NVIDIA GPU.
Browse, search, and analyze sessions from Claude Code, Codex, and other coding agents locally.
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui
Video translation & dubbing with voice cloning — 100% local, zero API. Supports 30 languages (VoxCPM 2), Qwen-Image-2.1 visual & thumbnail studio, YouTube SEO Studio, Viral Shorts Studio (9:16), and WordPress SEO Blog Post Generator.
Lightricks LTX-2.3 video generation (22B distilled-1.1) with a Gradio UI. Auto-detects GPU and configures offload.
Turn an image or prompt into a textured 3D asset on your own GPU. Install and start Foundry in Pinokio, then try the included ray-gun reference in Single Image or Text and export a GLB you can edit in Blender. Use local AI auto-rigging and the interactive rigging wizard to edit joints, test bends and export skinned GLB for Blender. The Foundry MCP is designed for Codex and Claude Code. It gives agents the same workflows and spatial rigging tools, including depth probes and live joint edits. Foundry also offers guided meshes, rigged hair, Gaussian splats and exports for games and 3D printing. Windows/NVIDIA preview. Available in English, Simplified Chinese, Latin American Spanish, French, Brazilian Portuguese, German, Japanese, Korean and Hindi. 用中文做出你的下一个 3D 素材! ¡Crea tu próximo asset en español! Créez votre prochain objet 3D en français ! Crie seu próximo asset em português! Erstelle dein nächstes 3D-Asset auf Deutsch! 日本語で次の3Dアセットを作ろう! 한국어로 다음 3D 에셋을 만들어 보세요! अपना अगला 3D एसेट हिंदी में बनाएँ!
Image-to-3D Gaussian splat generation from VAST-AI-Research. Requires a CUDA-capable GPU.
Mac-optimized YuE2 music generation using native MLX inference. Generate complete songs (melody, chords, vocals, accompaniment) from text prompts. Features an LLM Writing Room for lyric composition via OpenAI-compatible APIs (LM Studio, etc.). Pure Apple Silicon — no PyTorch needed.
