Freepik, the web graphic design platform, unveiled a brand new “open” AI picture mannequin on Tuesday that the corporate says was skilled completely on commercially licensed, “safe-for-work” photos.
The mannequin, known as F Lite, accommodates round 10 billion parameters — parameters being the interior parts that make up the mannequin. F Lite was developed in partnership with AI startup Fal.ai and skilled utilizing 64 Nvidia H100 GPUs over the course of two months, in keeping with Freepik.
F Lite joins a small and rising assortment of generative AI fashions skilled on licensed knowledge.
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 inventive: https://t.co/MyWsKer9Ir
• Texture model: is extra chaotic and error-prone, however delivers higher textures and… pic.twitter.com/GX5mIpYE8O
— Javi Lopez ⛩️ (@javilopen) April 29, 2025
Generative AI is on the heart of copyright lawsuits towards AI firms, together with OpenAI and Midjourney. It’s incessantly developed utilizing large quantities of content material — together with copyrighted content material — from public sources across the internet. Most firms growing these fashions argue truthful use shields their apply of utilizing copyrighted knowledge for coaching with out compensating the homeowners. Many creators and IP rights holders disagree.
Freepik has made two flavors of F Lite obtainable, commonplace and texture, each of which have been skilled on an inner dataset of round 80 million photos. Customary is extra predictable and “prompt-faithful,” whereas texture is extra “error-prone” however delivers higher textures and artistic compositions, in keeping 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.”
Freepik makes no declare that F Lite produces photos superior to main picture mills like Midjourney’s V7, Black Forest Labs’ Flux household, or others. The objective was to make a mannequin brazenly obtainable in order that builders might tailor and enhance it, in keeping with the corporate.
That being mentioned, operating F Lite is not any straightforward feat. The mannequin requires a GPU with not less than 24GB of VRAM.
Different firms growing media-generating fashions on licensed knowledge embrace Adobe, Bria, Getty Pictures, Moonvalley, and Shutterstock. Relying on how AI copyright lawsuits shake out, the market might develop exponentially.
