MiniMax H3 ⚡️ Spectrum acceleration in ComfyUI — 34% lower Euler sampling time, 30% lower RES time Tested at approximately 0.5 MP, 8 seconds and 20 steps on an RTX PRO 6000 under WSL, using High VRAM mode 👇

Hermes has been making strong progress in ComfyUI integration, self-evolving skills, and persistent memory. Pan aims to be its most comfortable “cockpit”: ✅ Clean chat interface and easy skill management ✅ Upcoming Crypto/AI skill marketplace ✅ Future collaboration: on-chain trading tools, personalized financial memory, and more We believe Pan + Hermes can become a practical and user-friendly Crypto AI Agent that helps users handle daily financial tasks with ease. Open to ideas and collaboration @NousResearch 👀

Lightx2v dropped 🙂 new Minimax-h3-Turbo LoRA (V1.0) for ComfyUI Settings: -4step (str-1.0, euler or er_sde, beta shift-12 for Video / 3 for Audio) -8step (str-1.0, res_multistep or euler / simple or beta) shift-12 for Video / 6 or 10 for Audio 👇

HappyHorse 1.1 is powering the next wave of AI video creation. From @ComfyUI and @runware to @fal , @replicate , and @Picsart , leading platforms are already building with it. Now available on Alibaba Cloud Model Studio. Start creating today: #HappyHorse# #AlibabaCloud# #ModelStudio# #AIVideo# #GenerativeAI#

New on ModelScope! Anima Tile & Repair ControlNet-LLLite v1.0, a small ControlNet for anime image repair that preserves the original composition and character structure. 🚀 🤖 🎨 Fixes blur, compression artifacts, noise, and low-quality degradation ✨ Tile-based local detail enhancement and sharpening 🖼️ Keeps original composition and character structure intact during repair ⚡ Python and ComfyUI ready V2 is in training with expanded task coverage, coming next week.