Iván de Prado
@ivanprado
Head of AI at @freepik
🚀Excited to announce F Lite: a new open-source text-to-image model by @freepik and @FAL! The first at this scale that’s both open-source and trained exclusively on licensed, high-quality data.🧵
Introducing Magnific Precision, now on the Freepik AI Suite Upscale your images while keeping the original intact. The lastest state of the art model by @Magnific_AI Available for all plans
Google Imagen 4 is now available on Freepik Yes, we’re shipping from the streets of San Francisco while @upscaleconf is happening Google Veo 3 coming soon 🔥
Three video models are now Unlimited 💥 MiniMax Hailuo 02, Seedance 1.0 Lite & Pro for zero credits Available for Premium + and Pro users
IT'S FINALLY HERE! 🔥 Magnific Precision 🔥 First we created the first Creative Upscaler. Now, we reimagine the new world standard for non-creative upscales! Perfect for photographers and creatives: just more resolution/detail without unwanted changes! Info + tutorials 🧵👇
Users of `torch.compile`. Some small performance tips: 1. Default to `fullgraph=True` to catch graph breaks as early as possible. 2. Check for recompilation triggers. Put your code under `torch._dynamo.config.patch(error_on_recompile=True)` context. 3. Use regional compilation…
Freepik users can now generate unlimited AI videos with Minimax 02, available until July 17. This is how we make content creation actually fast, and actually fun.
Unlimited AI video starts today MiniMax 02 by @Hailuo_AI is live for 7 days, no credits Premium+ and Pro users, the countdown starts now
Stay tuned
This month, we're not following the rules Tomorrow, something's happening on Freepik Get ready
Tired of credits? We too! Freepik introduces unlimited image generation so that you can create without worry.
Introducing unlimited image generation Create and edit images without losing credits, for every model Available for Premium + and Pro
Love this visual dive into flow matching, specially the interactive diagram at the very end dl.heeere.com/conditional-fl…. Thank you @LodestoneE621 for sharing 💪
This course on building language models from the scratch looks very interesting for people starting.
Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team @tatsu_hashimoto @marcelroed @neilbband @rckpudi. Researchers are becoming detached from the technical details of how LMs work. In CS336, we try to fix that by having students build everything:
Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team @tatsu_hashimoto @marcelroed @neilbband @rckpudi. Researchers are becoming detached from the technical details of how LMs work. In CS336, we try to fix that by having students build everything:
Veo 3 is now available Once again, we're delivering the latest version of the most precise AI video mode by Google Built-in audio and high-quality, lifelike camera movements and effects
⚡ What Freepik has achieved is insane How the hell did it go from being just a simple stock image site to becoming the all-in-one AI suite? Honestly, this should be case study material in entrepreneurship classes someday 😂 It’s wild what they’ve pulled off by stitching…
Open-sourcing nanoDiT -- an educational repository to show rectified-flow training of class-conditional DiTs for image generation (~600 LoC). Hope that helps: github.com/sayakpaul/nano…
So, you want access to Veo 3 faster inside Freepik, eh?... Well, maybe our CEO and 'bailaor' 😂 @cuenca can help you. Tag him in a comment!
looking for a staff/senior product designer who wants to be building the future of creativity + AI at @freepik reply or DM with the top designers you know, RTs super appreciated! fully remote or in-person in sunny Málaga