NVIDIA PiD Decoder: One-Step VAE Swap for 4K Diffusion
NVIDIA Toronto AI Lab open-sources PiD, a plug-in pixel diffusion decoder that replaces VAE in FLUX, SD3, and Z-Image to output 2K-4K in one distilled pass.
Perplexity Open-Sources Bumblebee Supply-Chain Scanner
Perplexity open-sourced Bumblebee, a read-only supply-chain scanner for macOS and Linux that detects compromised packages.
Framedex: Search Your Video Archive Locally with Gemma 4
A solo developer just open-sourced framedex, an MIT-licensed local pipeline that indexes a year of personal video footage on a 2021 MacBook using a quantized Gemma 4 31B model running through LM Studio.
Cohere Command A+ Opens 218B Apache 2.0 Frontier Model
Cohere released Command A+ under Apache 2.0 on May 21, 2026. The 218B sparse MoE runs on two H100s, with native citations and 48 languages.
Pixal3D Open-Sources Pixel-Aligned Image-to-3D Model
Tencent ARC open-sourced Pixal3D, a SIGGRAPH 2026 image-to-3D model generating high-fidelity meshes from single images.
NVIDIA Nemotron Diffusion: 3x Faster LLM Decoding
NVIDIA released the Nemotron-Labs-Diffusion family on Hugging Face, an open-weights LLM that switches between autoregressive, diffusion, and self-speculation decoding for 2.7x to 3.3x throughput gains.
Forge Gives Local AI Agents Enterprise-Grade Reliability
Open-source Forge framework adds guardrails to 8B local models, lifting agentic task reliability to 86.5% -- no cloud API required.
StemDeck: Free Local Audio Stem Separation
StemDeck v0.5.0 splits any track into vocals, drums, bass, guitar, piano, and other elements. Runs locally, free, no account required.
ByteDance Lance: 3B Open Model for Image and Video
ByteDance Research released Lance, a 3B Apache 2.0 unified multimodal model that handles image and video generation, editing, and understanding in a single framework. Strong VBench and GenEval scores.
Semble: Code Search for AI Agents Uses 98% Fewer Tokens
Semble gives AI agents semantic code search with 98% fewer tokens than grep+read. Indexes in 263 milliseconds. MCP-ready for Claude Code.
ComfyUI-Mesh Now Runs LTX 2.3 Across Two GPUs
ComfyUI-Mesh added LTX 2.3 support on May 17, splitting the 22B video model across two GPUs over gigabit Ethernet using NVENC codec compression.
Zerostack: A Rust Coding Agent With 8MB RAM
Zerostack is a pure Rust coding agent that launched May 16, 2026, running in 8MB of RAM compared to 300MB for JavaScript-based alternatives like Opencode.
DeepSeek-V4-Flash Makes LLM Steering Practical
DeepSeek-V4-Flash is the first local model competitive with frontier AI, making LLM activation steering practical for the first time. A guide for creators.
ComfyUI-DramaBox Adds LoRA Support for Custom Voice Training
ComfyUI-DramaBox added LoRA weight injection on May 16, letting creators load custom voice personalities into workflows without model reloads.
SANA-WM: Open-Source AI Generates 1-Minute 720p Video
NVIDIA's SANA-WM is a 2.6 billion-parameter open-source world model that generates 720p, 60-second video with 6-degree-of-freedom camera control on a single GPU.
Supertonic 3: On-Device TTS Speaks 31 Languages
Supertonic 3 is an open-weights, CPU-only TTS engine from Supertone with 31 languages, expression tags, and zero-shot voice cloning.
FLUX.2-klein-9B in ComfyUI: Sub-Second Image Gen
Black Forest Labs' FLUX.2-klein-9B now integrates with ComfyUI via NKD Klein Tools v1.7.0, enabling sub-second image generation with just 4 inference steps on an RTX 4090.
holaOS 0.1: AI Workstream Manager for Creators
holaOS 0.1 ships Dashboard, Sub Agents, and Multi Workspaces for managing parallel AI workflows on macOS.
Inside Bun's 1M-Line Rust Rewrite by Claude Code
Anthropic's Claude Code ported Bun from Zig to Rust in nine days: 1,009,257 lines, 99.8 percent test pass, 13,000-plus unsafe blocks. The case study.
IBM Granite Embedding R2: Open Multilingual RAG Models
IBM has released Granite Embedding Multilingual R2: a pair of Apache 2.0 embedding models with 32K context, 200+ languages, and a top MTEB score under 100M parameters. A drop-in swap for paid commercial embedding APIs.
VOID, BiRefNet, and Gemma 4 Are Now in ComfyUI
Three significant open-source models arrived in ComfyUI on May 14, 2026: VOID for video object deletion, BiRefNet for image segmentation, and Gemma 4 for multimodal reasoning.
Image-Blaster: One Image to 3D Worlds for Claude Code
Open-source Claude Code skill turns one image into a fully meshed 3D scene with separate object meshes, Gaussian splat background, and ambient plus physics audio in under five minutes.
LTX Director v1.3.0: ComfyUI Timeline Editor for LTX 2.3
LTX Director v1.3.0 dropped today: a single ComfyUI node that replaces your entire LTX 2.3 toolkit. Timeline editing, prompt relay, 8 keyframes, and custom audio, all in one place.
OpenReader v3: Self-Hosted TTS for PDF, EPUB, DOCX
OpenReader v3.0 converts PDF, EPUB, DOCX, TXT, and Markdown files into synchronized read-along sessions or exported audiobooks, with multiple TTS providers and Docker deployment.