MEGATHREAD

MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

Release Raylight 1.7.2 · komikndr/raylight Added MiniMax Support, 2x Speedup

astropuzzo/ComfyUI-MiniMax-H3-Image-Studio: Experimental, entirely AI-coded ComfyUI nodes for MiniMax H3 T2I, I2I, reference editing, arbitrary frames, and optimized still selection.

AsuraAce/ambit: Local-first desktop manager for AI image libraries

ArtefactDesigntn/Jebari-ImageBatch: Custom ComfyUI nodes for batch image loading

OpenSenseNova/SenseNova-U1: SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles V2

0xShug0/audio.cpp: All-in-one, inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and highly optimized performance. No Python dependency.

Elastic Diffusion Transformer

tin2tin/Asset_Generator-2D-3D: Blender asset generator for 2D and 3D

Boogu/Boogu-Image-0.1-Edit-Turbo · Boogu-Image-0.1-Edit-Turbo (Image-to-Image) released

shootthesound/Fizgig: LoRA Studio — Added Support for Krea 2 With Full Feature Parity

fal/LTX-2.3-3DREAL-LoRA · LTX‑2.3 IC‑LoRA — 3D render to Photoreal

SurrealByDesign/comfyui-krea2-sageattention-guard: Krea 2 / Krea 2 Turbo safe SageAttention patch and workflow for ComfyUI-KJNodes

xororz/local-dream: Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU inference. Added Anima support on mobile.

AHEKOT/ComfyUI_VNCCS_Utils: VNCCS 3.0 Release

TokenSpender/ComfyUI-Sidebar-Gallery: A searchable media gallery and metadata viewer for ComfyUI.

clark-labs/clark-air-sana-1.6b-1.58bit · A Sana 1.6B text-to-image transformer compressed to ternary (~1.85 bits/weight): 8.6× smaller than FP16, near-FP16 quality.

SamuelTallet/ZPix: Added Support for Krea 2 Turbo