Customizing Realistic Human Photos via Stacked ID Embedding https://huggingface.co/spaces/TencentARC/PhotoMaker-V2
Global radar
New projects people are discovering or following across Pinokio.
[NVIDIA ONLY] Gradio demo for Flux Kontext based on Diffusers with single and multiple images.
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui
[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM
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.
Separate Anything You Describe (https://huggingface.co/spaces/Audio-AGI/AudioSep)
A spy satellite simulator in your browser, except the data is real. No API keys needed.
Tencent Hunyuan AuK — 1.5B speech generation & editing. Rewrite what is SAID in an existing recording (fix a mispronounced word) while keeping the original voice and delivery. Also zero-shot TTS, emotion/timbre/whisper edits, denoise, dereverb and speaker separation. MIT licensed.
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation https://huggingface.co/spaces/ashawkey/LGM
A simple, high-quality voice conversion tool focused on ease of use and performance. https://github.com/IAHispano/Applio
Never stop coding. Free AI gateway: one endpoint, 160+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.
The modern Flyout app for Windows 11, built with Fluent 2 Design principles. Media Flyouts, Taskbar Widgets and more.
