🔴¡EL FIN DE FREEPIK...!
Y el comienzo de la era Magnific 🔥
Rebranding completo de Freepik que ahora pasará a ser Magnific, cambiando identidad visual, colores, web... ¡TODO!
Un cambio magnífico
@javilopen It is amazing, I realized that the sound is like somebody recorded it using a camera in the cinema, I wonder if it is required by prompt or a clue about the training dataset
Experimental chroma-radiance pixel-space model calibration results.
This 1024×1024 image only needs 1024 tokens!
not 4096 tokens like latent space models.
3-4× speedup!
latent space is officially dead!
And this is with just 50 param updates in so far.
🔥 We have improved Magnific Precision EVEN more.
Up to 10,000 x 10,000px 🤯
More detailed, yet completely faithful to your original image. FULL CONTROL. Don't ask how we did it!
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
Lo de Magnific estuvo guay y tal, sí.
Pero lo de Freepik... Lo de Freepik es de otra galaxia.
Lo de Freepik se estudiará en el futuro en clases de emprendimiento 🔥🔥🔥
⚡ 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 together every tool on the market (Magnific, all the video generators, everything from Flux, inpainting, outpainting, etc.) into one seamless workflow: from transforming any image with Flux’s latest to animating it, upscaling it, and turning it into a full-on video.
The whole thing flows smoother than sliding down a waterslide.
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 🔥
We've distilled the 10B F Lite Freepik's and Fal image generation model into a 7B parameters model, lighter. Read Javi's thread, as he explain the method he used with detail. And what worked and what not.
Remember the model was trained using only legally compliant images 😀
🚀 Meet F Lite 7B — Freepik’s new diffusion model distilled from F Lite. 30 % fewer params (7B vs 10B) with similar visual quality and same licensing and SFW properties as the original model. See thread for tech and method details! 👇
1/7 Ever noticed GPT‑4o images looking warmer than expected? You’re not alone. At @freepik, we've explored a simple scaling hack to neutralize that yellow cast - no heavy lifting required. ⬇️
Excited to announce the release of a fast, lightweight NSFW image detector! It delivers impressive metrics in evaluation. Check it out on Hugging Face https://t.co/lUw96LmGTn
We're thrilled to release our new EVA-based NSFW classifier, which detects content with stunning accuracy:
✅ High: 99.54%
✅ Medium: 97.02%
✅ Low: 98.31%
✅ Neutral: 99.87%
Outperforming popular models like Falconasai and AdamCodd! Amazing work @Ccabrerajimenez!