Introducing Figma node: connect any Figma frame into Weave workflows so you can → Create on-brand content at scale → Iterate, translate, or turn your designs into video → Edit and all connected assets stays up to date Available now to everyone.

Introducing Arrow 2 Our latest and most advanced models for generating precise, editable vector graphics. Higher quality. Faster outputs. Available now in App and API.

muse is absolutely nuts. wanted to see what was possible, so i gave it an @editframe api key, access to our render cloud, and a few other services. this video came out 🔥 we’ve always believed agents would need video infrastructure. once an agent can pull in context, compose video, and render at scale, a lot of things that used to be expensive or tedious become trivial. one personalized video or 10,000 of them. this is what we built editframe for.

I only have one thing to say to the AI Doomers: Pace deez open weights

switched back to opus for this one, and still pretty blown away recreating this @ElevenLabs video with @editframe 👀 see if you can spot the difference at the end sound on 🔊 took a bit of nudging, but the agent got really really close. take this for a spin, github repo is in the next post 👇

had so much fun using Astra to recreate the @bot videos the other day, I decided to send an agent to make more with @editframe . basically walked away and told the agent "recreate the videos on the official grok bot account nitter.net/bot/media " 👇github repo to try yourself in the next post ps, whoever is making these videos is nailing the personality of the brand. these little grok bots are so sweet!

How is the sound design? Not applying to get hired, just for fun :)

I tried to single prompt-shot your motion design using GPT-6 Astra + @editframe. Turned to out be great. Solid 8 / 10. Yours is ofcourse 10 / 00 @kirtanlb @yudDIDit #gpt6 #motiondesign

TsugiteがEditframe(@editframe )に対応しました 🎬 公式サンプル27種を、ブワーッと広げてみた。
ひとつひとつ、中の映像も動いています。 この告知動画も、Editframe公式サンプルをアレンジして制作。
つくりたい表現から選べるの、楽しい。 制作の仕組みはツリーに👇

Grok Bot can now buy things on the internet. To get started, connect @link, send your Bot shopping, and it can complete purchases on your behalf.

I have a couple upcoming launches, and need a cracked video editor. Couple of requirements: - Have made launch videos before - Not too expensive - Good communication skills If you know someone or are that person, drop your portfolio or DM it to me 👀

This is insane 🤯 Creating this entire storyboard with just one prompt using ChatGPT Image 2.5.

First off, Google Gemini is pretty incredible when it comes to motion, sequencing, video understanding, etc. training on YouTube probably helps :) All of the models are really good at Editframe, our abstraction has an edge and unlocks capability. Feel free to test or benchmark, but outcomes matter when you’re burning tokens 🔥 For most of these videos, I was using a recent sonnet or opus model to drive the agent. I would have the agent upload the video, analysis was being done via Gemini, that info/semantics was being fed back to the coding model, and so on. At that point, depending on how you prompted, it would compare and adjust. The things that matter are the semantics of what is happening, the LLM native framework (html/css, react), the temporal model (Editframe), and compute execution layer (Editframe) for feedback (how quickly something renders) Tbh I think anyone could get these results with not much prompting or video experience. The edge is @editframe

FIGMA MOTION IS HERE FIGMA MOTION IS HERE FIGMA MOTION IS HERE Live from Config 2026

It's been very cool to see these come through. This is a pretty clear example of LLMs just being able to succeed in different ways. And this way is chucking mountains of html and css at the problem. It's a good time to be built on a text format :D