Open-source generative AI models for image, video, audio and 3D creation
2K video with native stereo audio in one pass
Stage
Not given
Startup
Founded
2022
2026
Based in
GB
Not given
Pricing model
Freemium
Freemium
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.
On the Hailuo AI App: free tier and paid monthly plans (rates listed in app). On MiniMax Open Platform: billed per output second, with 2K tier priced above 768p tier. On this site: 18 credits per second at 768p and 29 credits per second at 2K, with annual plans showing 50% discount and various month
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
Multimodal reference input: images, video, and audio
Context-IR token-based pricing variant
Downloadable weights for local deployment
H3-Contextual Omni Representation for modality bridging
Up to 12 reference files with caption compression
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
Only model generating video and audio together natively
2K output at lower per-second rate than competitors
Downloadable open weights available
Accepts richer multimodal reference input than competitors
Stability AI
MiniMax H3