Freepik, the net graphic design platform, unveiled a brand new “open” AI picture mannequin on Tuesday that the corporate says was educated solely on commercially licensed, “safe-for-work” photos.
The mannequin, referred to as F Litecomprises round 10 billion parameters — parameters being the inner parts that make up the mannequin. F Lite was developed in partnership with AI startup Fal.ai and educated utilizing 64 Nvidia H100 GPUs over the course of two months, in line with Freepik.
F Lite joins a small and rising assortment of generative AI fashions educated on licensed information.
We’ve been secretly engaged on this for months! It feels good to lastly share it!
LINKS:
• Common model: extra predictable and prompt-faithful, however much less creative: https://t.co/MyWsKer9Ir
• Texture model: is extra chaotic and error-prone, however delivers higher textures and… pic.twitter.com/GX5mIpYE8O
– report Lopez ⛩️ (@javviloPen) April 29, 2025
Generative AI is on the heart of copyright lawsuits towards AI corporations, together with OpenAI and Midjourney. It’s steadily developed utilizing huge quantities of content material — together with copyrighted content material — from public sources across the net. Most corporations creating these fashions argue truthful use shields their apply of utilizing copyrighted information for coaching with out compensating the homeowners. Many creators and IP rights holders disagree.
Freepik has made two flavors of F Lite out there, commonplace and texture, each of which had been educated on an inner information set of round 80 million photos. Normal is extra predictable and “prompt-faithful,” whereas texture is extra “error-prone” however delivers higher textures and artistic compositions, in line with the corporate.
Right here’s a picture from the usual mannequin generated with the immediate “An individual standing in entrance of a sundown, in majestic environment.”
An AI-generated photograph from Freepik’s F Lite mannequin.Picture Credit:Freepik
Freepik makes no declare that F Lite produces photos superior to main picture turbines like Midjourney’s V7, Black Forest Labs’ Flux household, or others. The purpose was to make a mannequin overtly out there in order that builders might tailor and enhance it, in line with the corporate.
That being mentioned, working F Lite is not any straightforward feat. The mannequin requires a GPU with not less than 24GB of VRAM.
Different corporations creating media-generating fashions on licensed information embody Adobe, Bria, Getty Photos, Moonvalley, and Shutterstock. Relying on how AI copyright lawsuits shake out, the market might develop exponentially.
