Claude Code + Gemini Omni + GPT Image 2 is f*cking cracked
i just built an AUTOMATED AI UGC content system that generates full ad creatives end to end
drop in your product photos and a one line pitch, and the system analyzes your brand, generates a realistic AI avatar, writes the script, renders the video, adds captions, and stitches everything together. in literally one click.
if you're still wasting hours generating videos or hiring expensive editors with long turnaround times, this is for you..
here's how it works:
> drop in your product photos and brand info
> the system finds a reference image that matches your target audience
it generates a detailed JSON prompt and creates a hyper realistic starting frame
> feeds everything into Gemini Omni and renders the full video with voice
outputs and captions, all ready to post and all through Kie AI MCP or Higgsfield MCP (you have full control)
the whole process runs inside Claude Code. so you're not jumping between 6 different tabs trying to piece things together. one system handles everything
its only a 3 minute setup and 4-12 min per ad. each 30 second ad costs under $3 in API credits which is way cheaper than any editor and 10x faster..
RT + reply "UGC" and i'll send it over (must follow so i can dm)
Fascinating conversation of the future of AI design tools and workflows. @figma as a long time fan and investor I sure hope you’re on top of this! Becoming the “infinite canvas” for agent-human and human-human collaboration seems like an obvious future I’d be willing to bet on.
9 months ago, I listened to @stephenhaney predict the state of tools in 2026.
Today, you'll hear him predict the future of software-making tools, and it's the best I've heard.
He's building @paper who just dropped their Desktop MCP and it feels like the familiar pre-AI workflows just became fluid.
Your canvas can now talk to Claude Code, Cursor, whatever you're using.
I talked to him about why his team canceled Figma and what the future software building stack looks like.
New State of Play.
https://t.co/Erf7gxKCaL
@ggerganov love your work. what do you recommend for creating an LLM restricted to local files and data only? Think NotebookLM - can this be done with llama.cpp or using any open source tools? I want to build a NotebookLM version on my localhost using nothing but a Macbook CPU
@adamwathan@adamwathan Any plans to create these tailwindUI templates in vue for vue.js devs? A lot of folks in the laravel ecosystem default to vue.js