🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Veo 3 now supports start frames. now you can create Veo 3 videos using any image as the starting frame! try it now in Krea Video.

new ChatGPT Image with improved consistency. this new model from OpenAI keeps input images way more consistent than its previous version. try it now!

Lock in ✨get off grid KREA AI

Published 0.0.9 version of imscore 1. Added EvalMuse (used for SeedDream 2.0 evals) 2. Added preliminary support for CycleReward (contrib Naga/Abhi) 3. Added VQAScore (used for Imagen 3 evals) github.com/RE-N-Y/imscore

Ramtin Naimi started a successful hedge fund at 19, went bankrupt at 24, and then built a $1.8 billion venture firm backed by investing icons like Stanley Druckenmiller, Marc Andreessen 🇺🇸, and Bill Ackman. Michael Ovitz calls Naimi his “non-biological son.” Founders say he’s “the most

introducing Motion Transfer. this new tool powered by Runway's Act-2 lets you control the movements of any character with precision. tutorial below 👇

introducing Wan 2.2 this new open-source model can generate high quality videos in less than a minute and it will soon support custom styles! try it now in Krea Video.

Today we are releasing FLUX.1 Krea [dev] - a new state-of-the-art open-weights FLUX model, built for photorealism. Developed in collaboration with KREA AI, this model is focused on images with unique aesthetics. No “AI look”, no blown-out highlights, just natural detail.

it's out 🫡

New Model Drops: FLUX.1 Krea [dev] x ComfyUI Developed by Black Forest Labs x Krea collaboration 🔹 Unique aesthetics, no "AI look" 🔹 Natural details, no blown-out highlights 🔹Exceptional realism and image quality 🔹 Fully compatible with FLUX.1 [dev] architecture This is

FLUX Krea [dev] uses the same infrastructure than FLUX.1 [dev], which means all fine-tuning tools should work out of the box: diffusers, Ostris, Kohya Tech, etc who's gonna release the first FLUX Krea LoRA? 👀

Black Forest Labs foundation model expertise + KREA AI's applied AI focus = best open-weights FLUX model to date

Meet Producer, your personal AI music agent. It turns your imagination into music. Powered by FUZZ-2.0, the new state-of-the-art model from the Riffusion team. Welcome to the studio.

we are answering questions about the model on hacker news

WAN 2.2 image generation + a basic 4K GAN upscale is absolutely stunning try the combo KREA AI. prompts in alt

introducing Wan2.2 Image. it turns out this video model can also produce great image results with incredible prompt adherence! try it now in Krea Image.

introducing Aleph. this new video model from RunwayML allows you to edit videos using text prompts. try it now in Krea Restyle.

introducing Qwen. this new image model comes with great prompt understanding and text rendering. try it now for free in Krea Image.