I feel like I have the force genuary day 10: generative music #genuary10 #genuary2023

building a personal code art tool, pretty fun to explore all the parameters of a piece

drifting away still images

genartclub.com was gone. It's back! 🎉 The domain lapsed a few months ago and took the site down with it. I bought it back yesterday and rebuilt the whole thing from the last Internet Archive capture, with the club's blessing. genartclub.com

new portfolio — 1,600+ images and videos of art I've made across various mediums over the last 4 years: • are.na-style grid with video & gallery image previews on hover, adjustable columns, shareable post links • hdr image + video support in the fullscreen viewer • tag filtering across medium, style, subject, technology, year & media type (stack tags to drill down further) • keyboard shortcuts - ‘c’ for toggling visibility of post captions, ’t’ for toggling sidebar visibility under the hood, I built a custom CMS to manage and view all media: • vanilla js, html, css - no framework or dependencies • static site + cloudflare workers (d1 database, r2 storage) • media processing happens in-browser at upload, keeping the backend small (~$5/mo for everything) • frontend admin portal for managing and publishing media hope you enjoy checking it out. the cube in the header spins if you drag or click it!

Most AI tools are a black box. You put something in and have limited say over what happens in between. For production pipelines, that's a dealbreaker. Silverside, an AI innovation lab running full production pipelines for advertising, needed a different approach. Node-based, auditable, and fully controllable at every step. They built on ComfyUI. " We needed to go beyond what a single person in the backyard could do. That's when comfy UI really comes in . You can break your production into little nodes, adjust one thing, and everything in your pipeline adjusts automatically. " - @Silverside_AI, Co-Founder, Silverside That granularity matters at studio scale. Silverside isn't prompting their engineering workflows. Each node is an explicit decision point: model selection, conditioning, sampling parameters, compositing logic. The graph is the pipeline, and it's fully reproducible. The result is generative output that carries intentional craft. Not because an artist got lucky with a prompt, but because the workflow was designed to produce it consistently. That's the difference between a tool built for consumers and infrastructure built for production. If you're a TD, pipeline engineer, or generalist figuring out where ComfyUI fits in a real production environment, see how Silverside uses ComfyUI as a full production engine.

We just raised $30M at a $500M valuation, bringing our total funding to $47M. Led by @craft_ventures , with @PaceCap , @chemistry , TruArrow, and others. But before anything else: this belongs to the community. ComfyUI started as one developer and one open-source repo. No roadmap. No company. Just creators who wanted real control over how they built with AI. That community is now: → 4 million users → 60,000+ community-built nodes → 150,000+ daily downloads Every number traces back to people who built in the open, for anyone to use. Here's where the funding goes: → Comfy Cloud: for teams and studios that need security and scale → Collaborative workflows: versioning and iteration built for how studios actually work → A better local experience: more seamless, more stable → Ecosystem reliability: making 60,000+ community nodes more dependable → Day-one model support: every major release, compatible at launch We are not building a walled garden. We are building open infrastructure, built to last. Thank you genuinely, The ComfyUI Team

My dear front-end developers (and anyone who’s interested in the future of interfaces): I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept): Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

finally set up openclaw this week on my raspberry pi, anybody got tips for the best setup?

You are morally obligated to move from Vercel:

@LumaLabsAI gave us early access to Ray 3, and we put it to the test From subway scenes to giant creatures — we turned the chaos of Ray 3 into something beautiful. Ten artists, one surreal world. Check out Luma Labs Ray 3 model — out now!!!

I worked with Silverside AI on Panasonic’s Porsche designed product launch ad in China Mass AI adoption is going global at unprecedented speed!

experimenting with ascii

My entry! Made the base with bolt then went into cursor to edit further. And deployed on vercel bolt-website-neon.vercel.app

genuary day 7: use software that is not intended to create art or images created a bash script to make 100 chrome windows appear randomly on my screen. almost crashed my computer haha