BiasMedium
Stable Diffusion Reportedly Exhibited Biases for Prompts Featuring Professions
- Occurred
- Aug 22, 2022
- Published
- Jun 8, 2023
- Source
- AI Incident Database
Summary
Stable Diffusion reportedly posed risks of bias and stereotyping along gender and cultural lines for prompts containing descriptors and professions.
Developers
- Stability AI
- Runway
- LAION
- EleutherAI
- CompVis LMU
Deployers
- Stability AI
Harmed parties
- Women
- Minority groups
- Women and girls
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: The incident involves Stable Diffusion exhibiting gender and cultural bias in profession-related prompts.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8