Microsoft Lens in ComfyUI is Very Fast!
ComfyUI now has support for the Microsoft Lens model. Lens is a 3.8B-parameter foundational text-to-image model designed for efficient training and fast high-resolution generation. It combines dense-caption pre-training, mixed-resolution learning, GPT-OSS multi-layer text features, and the FLUX.2 semantic VAE to reach competitive quality with substantially less training compute than larger T2I models. Trained on Lens-800M, an 800M image-text corpus with long GPT-4.1 captions, maximising information density per training batch. A 48-block MMDiT denoiser leverages FLUX.2 latents and concatenated multi-layer GPT-OSS features for stronger prompt following and multilingual generalisation. Mixed-resolution training enables inference across aspect ratios from 1:2 to 2:1 and resolutions up to 1440×1440. And if that isn't enough, the distilled Lens-Turbo supports fast 4-step generation for images in seconds! In this video you'll learn not only how to do basic text-2-image generation with Lens, but also how to use the model for inpainting and upscaling tasks too for improved image quality. All via easy-to-follow, step-by-step instructions from an actual human tutor :) == Get Workflows! == Looking to support the channel? Or perhaps you just want to have the featured workflow READY-MADE for you instead? You can skip the DIY to jump straight in using the link below: / microsoft-lens-159496626 Create or don't - the choice is yours! == Join this channel to get access to perks == / @nerdyrodent == More Links == ComfyUI - https://github.com/Comfy-Org/ComfyUI MS Lens - https://huggingface.co/microsoft/Lens == Comfy Cloud == Worried your computer isn't up to the job? Think you don't have enough RAM or VRAM and don't want to even try on your own PC? Then why not jump straight to Comfy Cloud - the easiest way to use Comfy online without worry! https://www.comfy.org/cloud (Now with FREE tier! - https://blog.comfy.org/p/free-tier-ar...) == Beginner's Guides! == Just starting out? ComfyUI has been around for a while now, but my older videos still stand strong and give you the BEST base to start from. LEARN how to get Comfy installed the RIGHT way. Avoid those weird, obfuscated installers which stunt your learning. Skip the confusion + any strange errors in the future from using an installer. UNDERSTAND the workflow creation process. 1. Installing Anaconda for MS Windows Beginners - • Anaconda - Python Installation made Easy! ... 2. Installing ComfyUI for Beginners - • How to Install ComfyUI Properly - Avoid Po... 3. ComfyUI Workflows for Beginners - • ComfyUI Workflow Creation Essentials For B... == The VERY BEST ComfyUI Playlist! == Is this tutorial too advanced? Do you need to learn more? Don't worry - I've got YEARS of video tutorials! Go back to where it all started and catch up in no time from a REAL HUMAN TUTOR: • The VERY BEST ComfyUI Tutorial Course on Y... == Computing == 🔧 For a viable AI experience using your own hardware, I suggest: Ubuntu (I am because we are) 🐦 An Nvidia GPU (16 GB VRAM min, 24+ GB better) 64+ GB RAM 2+ TB SSD CPU with 6+ cores

Be Lenient and Easily Switch Your Refiner in ComfyUI

Gemma 4 12B on a 16GB Mac Mini Is Surprisingly Capable

Microsoft's new OS ... might actually work!

LongCat Image & Image Edit - Native Support now in ComfyUI!

Gemma 4 + New ComfyUI Nodes That Make Prompting Easy! (Ep18)

Forget Zune. Forget Vista. Copilot Is Microsoft's Biggest Failure

Z-image Advanced Tutorial: Controlnet, inpainting, 4K+ upscaling & more

I Hacked This Temu Router. What I Found Should Be Illegal.

Pixal3D on 6GB VRAM — Better Than Trellis 2! (Free & Local)

Ultimate Beginner Guide to Learning ComfyUI (2026)

You Can't Ignore AI in 3D Art Anymore (Here's the Real Workflow)

Using LTX2.3 Union & Abliterated CLIP in ComfyUI

LTX 2.3 - The New KING Of UNCENSORED AI VIDEO

Master Gemma 4 in 20 Minutes

Unreal Engine 5.8 New Features Explained!

NVIDIA PiD Setup in ComfyUI - 4K AI Images Without an Upscaler

Claude Opus 4.8 vs Qwen3.6 27B | Local vs Cloud Head-to-Head

Best 3D AI Generator Now Runs on 6GB VRAM! (Free & Local)

Longer LTX-2 Videos (lower peak VRAM) + Pose & Canny Controls in ComfyUI!

