MSP-Bench
Explore score history ↗MSP-Bench evaluates multi-subject personalized text-to-image generation. It scores identity fidelity, attribute binding accuracy, and attribute misalignment through a dual-pathway protocol.
- Released
- 2026-08-04
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
MSP-Bench paper and code
No reported scores are on record for this benchmark yet.