ImageLayered
Web AI tool (not autonomous): decomposes a user-uploaded flat image into named, editable transparent RGBA layers that can be moved, recolored, or exported as standalone transparent PNGs. Two modes: Quick (from $0.05/layer, JPG/PNG/WebP/GIF up to 5MB) and Precision (up to 16 layer
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for ImageLayered, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Web AI tool (not autonomous): decomposes a user-uploaded flat image into named, editable transparent RGBA layers that can be moved, recolored, or exported as standalone transparent PNGs. Two modes: Quick (from $0.05/layer, JPG/PNG/WebP/GIF up to 5MB) and Precision (up to 16 layers plus base, PNG/JPEG >=512x512). Also includes a built-in text-to-image generator. No goals, no memory, no external tool/API use, no multi-agent interaction; single-shot processing of user-provided images. Core model: open-source Qwen-Image-Layered (Apache 2.0).
Key features and capabilities
- Decompose an uploaded image into named editable layers (up to 16 in Precision mode)
- Export each layer as a standalone transparent PNG
- Text-to-image generation via built-in generator
- Free welcome credits for first-time users
AIVSS capability and automation profile
Autonomy level 3: Agent acts after approval
Additional agentic capability factors
- Opaque reasoning or action chain
- Non-deterministic behavior
Self-reported capability indicators; the AIVSS threat-model score below is generated separately and is not a certification.
MAESTRO 7-layer architecture
Architecture supplied by the signed-in listing owner.
Qwen-Image-Layered (open-source, Apache 2.0) for layer decomposition; hosted GPT Image 2.5 for the built-in generator.
Standard account auth; credit-based billing; no user data used for training beyond uploaded images processed per request.