Open-source generative AI models for image, video, audio and 3D creation
Aesthetic-first AI image generator with style control and creative direction tools
Stage
Not given
Not given
Founded
2022
Not given
Based in
GB
Not given
Pricing model
Freemium
Not given
Pricing
Free for non-commercial use and for commercial use up to $1M annual revenue under Stability AI Community License. Enterprise License available for organizations with annual revenue exceeding $1M.
Annual plans (50% off launch offer): Starter $9.9/month (9,600 credits yearly), Pro $19.9/month (24,000 credits yearly), Studio $44.9/month (72,000 credits yearly). Monthly and one-time credit packs also available.
Key features
Stable Diffusion 3.5 Large with 8.1 billion parameters for superior quality and prompt adherence
Stable Diffusion 3.5 Large Turbo generates high-quality images in 4 steps
Model requires only 9.9 GB of VRAM to unlock full performance
Diverse outputs with different skin tones and features without extensive prompting
Generates wide range of styles including 3D, photography, painting, line art
Stable Audio 2.0 generates full tracks up to three minutes at 44.1 kHz stereo
Stable Video Diffusion transforms images into 2-second high-quality videos
Fine-tuning and customization with Query-Key Normalization for flexible base models
ControlNets for Stable Diffusion 3.5 Large including Blur, Canny, and Depth
Expressive text-to-image generation with aesthetic diversity
Style references with adjustable per-reference strength
Moodboard direction for coherent visual language
Adjustable creativity levels from raw to high
Medium and Large model variants
Krea 2 Turbo speed-optimized variant
Up to 9 reference image slots per generation
4K resolution export capability
Prompt expansion for richer visual briefs
Commercial-use licensing on all paid plans
What makes it different
Runs on standard consumer hardware without heavy demands
Highly customizable models designed for flexible base to build upon
Ownership of generated outputs without restrictive licensing implications
Leads market in prompt adherence and rivals larger models in image quality
Separates subject intent from aesthetic intent for precise style exploration
Top-ten placement on Artificial Analysis text-to-image leaderboard
Open-source model weights available on Hugging Face
Wider aesthetic vocabulary covering raw, photographic, illustrative, and painterly styles
Designed for early art direction when exploration matters more than a single polished answer
Stability AI
Krea 2