Open-source generative AI models for image, video, audio and 3D creation
Multimodal annotation platform for skilled work
Stage
Not given
Not given
Founded
2022
Not given
Based in
GB
DE
Pricing model
Freemium
Contact for pricing
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.
Not given
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
First-person video capture with head, helmet or chest-mounted cameras
Dual-reviewed annotation of tasks, tools, objects and outcomes
Privacy processing including face and text removal before release
Documented protocols agreed before recording begins
Contributor consent tracking and payment per accepted hour
Provenance records with capture context, protocol version and processing history
Evaluation, research, commercial and enterprise licence tiers
Custom dataset collection for specified tasks and environments
Formats: MP4 video, Parquet tables, JSON manifest
Immutable, versioned releases for reproducible experiments
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
Real-world field recordings from skilled professionals instead of lab or simulated data
Includes failure and recovery episodes with explicit outcome state labels
Contributors are paid upfront agreed rates with transparent review decisions
Quality assurance with sample re-annotation and written acceptance criteria
ISO 27001 and SOC 2 Type II certification in progress