Features
Text-to-image generation from natural language
Text-to-video generation and editing via text (Aleph 2.0, up to 30s clips)
3D model generation with scalable mesh and GLB export
Video upscaling to 4K resolution
Model Discovery: top models per media type with optional preference settings
My Files: centralized asset library for all creations and imports
Traceability with awen.zip: export asset and full lineage
Fine-tuning: import knowledge, processes, visual data, refine via chat
Team collaboration with workspaces and role-based access
Parallel execution via sub-agents for batch processing
SOC 2 Type II compliant with encrypted data at rest and in transit
Data ownership: no training on your data, isolated workspaces
Capacity estimator for planning usage across media types
Visual Generative Language (VGL) for structured control over lighting, camera, composition
Full IP indemnification on generated outputs
Licensed training from Getty Images, Alamy, Envato
SOC 2 Type II, ISO 27001, GDPR, EU AI Act compliance
Deploy on cloud, BYOC, on-premise, or air-gapped
APIs, SDKs, iFrames, MCP, ComfyUI, Photoshop/Figma plugins
11 native AI nodes in Foundry Nuke
12 AI tools in SideFX Houdini
Fine-tuning suite for custom style models
Visual birth certificate per project/unit
Background removal, eraser, gen fill & expansion
Video background removal, replacement, upscaling
Product shot generation (lifestyle by text/image)
