Incident 529: Stable Diffusion Exhibited Biases for Prompts Featuring Professions
Description: Stable Diffusion reportedly posed risks of bias and stereotyping along gender and cultural lines for prompts containing descriptors and professions.
Entities
View all entitiesAlleged: Stability AI , Runway , LAION , EleutherAI and CompVis LMU developed an AI system deployed by Stability AI, which harmed racial minority groups , Women and gender minority groups.
Incident Stats
Incident ID
529
Report Count
3
Incident Date
2022-08-22
Editors
Khoa Lam
Incident Reports
Reports Timeline
gizmodo.com.au · 2022
- View the original report at its source
- View the report at the Internet Archive
This image was created with Stable Diffusion and listed on Shutterstock. While the AI is capable of drawing abstract images, it has inherent biases in the way it displays actual human faces based on users' prompts. (Image: Fernando_Garcia, …
bloomberg.com · 2023
- View the original report at its source
- View the report at the Internet Archive
The world according to Stable Diffusion is run by White male CEOs. Women are rarely doctors, lawyers or judges. Men with dark skin commit crimes, while women with dark skin flip burgers.
Stable Diffusion generates images using artificial in…
twitter.com · 2023
- View the original report at its source
- View the report at the Internet Archive
🚨 Generative AI has a serious problem with bias 🚨 Over months of reporting, @dinabass and I looked at thousands of images from @StableDiffusion and found that text-to-image AI takes gender and racial stereotypes to extremes worse than in …
Variants
A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.