Chris Barber

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

@krea_ai Congrats on the release! Awesome stuff

this is Krea 2. our first foundation model, built completely from scratch for aesthetic diversity and stylistic control. learn more and get early access 👇

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.

@AnhPhuNguyen1 @bit_of_rei Sweet!! Yeah would love to chat - great video @bit_of_rei

@code_rgb thanks Chris! you should meet @bit_of_rei one of our team members who lead this video both of y’all work in art and tech

with Mira, AI can now live on your face. capture every conversation. create the most personalized form of AI ever. order now.

@stevelauda_ I’ve been using it a good amount and a bunch of people in my company too. It’s great for variations of designs + decks

Who is actually using Claude Design? Anyone?

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

@MoriYuzan For sure, I don't think they are at the same level right now but with the rate of improvement in the video model space, I could see it happening in a year or less honestly

@code_rgb yes, you can generate shots but are they actually up to par with a hollywood movie standard? I'd love to see a 1 minute clip that can go toe to toe with an iconic 1 minute matrix scene.

I've been saying this forever. You'll never see an ai gen movie live up to anything that's currently out. the cost alone will fck you. it'll never escape the experimental stage. x.com/i/status/20465…

@zan2434 @eddiejiao_obj @drewocarr Insanely cool, how did you optimize LTX so much?

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see. @eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)

@Hadley Cursor is great, I use it every day over claude code and codex

I’m just a lowly seed investor, but I don’t get Cursor at $50B. Every frontier dev I know has moved off Cursor and off IDEs entirely. Only laggards are still on it. And dev tools always move from thought leaders to laggards, never the reverse.

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

@vikhyatk This is so sick! Going to integrate it into my tool soon

Real-time Moondream inference using our new inference engine

@QuiverAI Are you guys on Fal AI?

5 things you loved about our model Arrow. 1/5 Watching Arrow draw SVGs in real-time

@rehan_shei pretty awesome -- what model?

Built Diffusion Canvas an infinite 2D canvas where every direction is a different prompt. Define two semantic axes, pan around, and images generate in real-time as you explore the latent space. Every pixel coordinate is a unique point in embedding space.

@LTXStudio You can generate a new video by typing in a location at the top (takes around a minute and a half to generate)

Weekend project: Experimented with LTX 2.3 (@LTXStudio) to make infinite CCTV cameras of different locations. Looking through these feels like interdimensional cable from Rick and Morty. Check it out: infinitecctv.com

@alisaqqt That’s cheap compared to Veo 3.1 and Kling 3.0

Seedance 2.0 update: The API pricing was just dropped. Video input included: ¥46/M tokens (~$6.67/M) Video input excluded: ¥28/M tokens (~$4.06/M) A 15-second video costs ~¥15($2.17). That's literally ¥1 ($0.14) per second. Do you think that's expensive? 🤔

@ivanhzhao @NotionHQ Hmm I was trying it out and then it wouldn't let accept an actual task? I can only reject or delete the page

At @NotionHQ, we believe every business deserves powerful & beautiful tools. AI is the most important technology of this era. It shouldn't only belong to companies that have AI teams or can afford forward deployed engineers. Today we're launching Custom Agents: — The first multiplayer agents built for business. — No coding. Minutes to set up. Hosted in the cloud. — Run autonomously 24/7 with all your business apps. — Switch between the best LLMs (usually the same day they're released). — One person builds it, the whole company benefits. Rolling out for Business and Enterprise customers today. The AI era should leave no one behind 👌

@fredrikalindh What do you when a code base has a frontend repo and a backend repo that need to run? Is the agent able to handle two repos? I couldn’t add more than one on the interface

i joined cursor a month ago to build cloud agents - today we’re launching agents that can test and demo their work last week i shipped 60 PRs with them this is how i use them:

@AIWarper just waiting until feb 24 😔

Can i just like.... get access to Seedance 2 already so I can make content? This waiting feels like an eternity and there is nothing else I have the drive to even test right now