Krea 2 Raw is Krea AI’s base open-weight text-to-image diffusion checkpoint, designed primarily for fine-tuning, LoRA training, and post-training rather than direct inference. It is part of the Krea 2 model family and uses a 12-billion-parameter Diffusion Transformer architecture to generate images from natural-language prompts. Unlike Krea 2 Turbo, which is distilled and optimized for faster direct generation, Raw is the foundational checkpoint before additional post-training and fine-tuning. This makes it especially useful for developers, researchers, and creative teams who want to customize the model for specific styles, domains, products, or visual workflows. It supports Diffusers, the official Krea codebase, and SGLang, and it can be used to train LoRAs that are later compatible with Krea 2 Turbo. Krea 2 Raw is intended for image generation, concepting, design exploration, visual production, and creative tool integration under the Krea 2 Community License.

Features

  • 12B-parameter Diffusion Transformer architecture
  • Base checkpoint before post-training and distillation
  • Designed for fine-tuning, LoRA training, and customization
  • Generates images from natural-language prompts
  • Compatible with Krea 2 Turbo LoRA workflows
  • Supports Diffusers, SGLang, and official Krea codebase
  • Useful for concept art, design exploration, and visual production
  • Released under the Krea 2 Community License

Project Samples

Project Activity

See All Activity >

Categories

AI Models

Follow Krea 2 Raw

Krea 2 Raw Web Site

Other Useful Business Software
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Krea 2 Raw!

Additional Project Details

Registered

2026-06-29