Krea 2 Technical Report - Krea
Technical report for Krea 2 (K2), our open-weights text-to-image foundation models for creative exploration. Release includes K2 Raw and K2 Turbo open weights.
Introduction Over the past few years, image generation has seen remarkable progress. Diffusion and flow-matching models can generate high-resolution images, produce sharp photorealism and stable structure, render dense text, encode broad world knowledge, and follow user prompts in precise detail. These improvements have been driven by several interacting factors including scalable transformers architectures, improved captioning and text encoders, better latent representations, and pipelined post-training techniques. Yet as the field has optimized for reliability on these capabilities, many…
saved by
related reading
- Composer2.pdfcursor.com
- Open Weights for FLUX.1 Kreakrea.ai
- frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
- Kimi K2.5 Tech Blog: Visual Agentic Intelligencekimi.com
- Diffusion models from scratchchenyang.co
- The Illustrated Stable Diffusion – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
- laguna-m1-xs2-technical-report.pdfpoolside.ai
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Scalable Diffusion Models with Transformersopenaccess.thecvf.com
- 2403.09611.pdfarxiv.org
- Let's reproduce GPT-2 (124M)youtube.com
- FLUX.1 Krea [dev]: An ‘Opinionated’ Text-to-Image Modelbfl.ai