Highlights
Personal stories I keep coming back to.
Latest posts
Notes from the workshop floor.
Qwen-Image-2.1 Viggle Turbo: 4-Step Distilled DiT in Diffusers and ComfyUI
Accelerate Qwen-Image-2.1 generation by 10x with Viggle Turbo. Master 4-step DMD2 distillation, LoRA adapters, GGUF quants, and ComfyUI workflows.
Qwen-Image-2.1 ncnn Vulkan: Run 7B DiT on 2GB VRAM Without CUDA
Run Qwen-Image-2.1 locally on Intel, AMD, and Mac GPUs with 2GB VRAM. Master nihui's portable C++ ncnn Vulkan engine without Python, PyTorch, or CUDA lock-in.
OpenCreator Explained: Open-Source AI Video Subtitling & Dubbing
Deep dive into OpenCreator (formerly KrillinAI), an open-source Go & Electron engine that transcribes, translates, dubs, and reframes videos into vertical shorts.
Jev Ultrafast Explained: Sub-20ms Decision Engine for Browser AI Agents
Mổ xẻ jev-ultrafast: sub-20ms browser agent speed, atomic DOM extraction, and the brutal truth behind TypeSafe vendor lock-in and cherry-picked benchmarks.
OpenHuman Explained: The 40k-Star Local AI Superintelligence & Obsidian Memory Engine
Explore OpenHuman, the 40k-star open-source local AI superintelligence featuring Karpathy Obsidian memory trees, TokenJuice, and multi-agent graphs.
Qwen-Image-2.1 Uncensored: Run Unrestricted ComfyUI with GGUF & Heretic
Master running Qwen-Image-2.1 Uncensored in ComfyUI using GGUF DiT and Heretic Text Encoder. Bypass refusal filters and optimize VRAM on RTX and Apple Silicon.
TypeSafe AI Explained: Inside the $40M Machine-Native System 1 Engine
Explore TypeSafe AI, the $40M System 1 intelligence engine. Learn how Jev primitives, RLCD calibration, and speculative fan-out power tools like jev-ultrafast.
Voice-Pro Explained: Local AI Dubbing & Voice Cloning Studio
Discover Voice-Pro, the open-source local AI dubbing studio combining Whisper, Demucs, F5-TTS, and CosyVoice with uv for zero-subscription voice cloning.
VoiceStudio Explained: The 33k-Star Local AI Voice & Dubbing Engine
Explore VoiceStudio, the 33k-star open-source ElevenLabs alternative with 646 languages, OmniVoice cloning, voice design, and native MCP agent support.
From the HoangYell galaxy
Sister projects I quietly maintain.Gallery
The friendly Astro image gallery - lightbox, pyramid layout, dark mode.
gallery.hoangyell.com
Yellorn
One browser tab for dirty data and webhook debugging - JSON, XML, YAML, CSV, mock APIs.
yellorn.com
Markdy
Animated architecture & system diagrams as code - 17 layout engines, Well-Architected linter, and browser-native motion.
markdy.com
Yell Chat
Casual AI chat playground I built to test ideas - yes, it talks back.
chat.hoangyell.com