Why AI food looks like that
Experts explain why AI-generated food images look unappetizing, citing diffusion model limitations, weak structural reasoning, and stylized training data.
The Verge examines why AI-generated food imagery from restaurants and brands often appears grotesque, citing researchers from Oxford, Naples, Zurich, and London. Diffusion models recover coarse structure before fine texture, so structural errors like extra fingers or donut shrimp get baked in early. Researchers note the models are weak at thin, continuous, terminating structures such as noodles, and reproduce the glossy conventions of professional food photography without understanding the objects. Odd internet imagery and memes in training data further skew outputs toward strange textures and clustered holes.
- Diffusion models recover coarse structure first, then add texture on top of early structural errors
- Models struggle with thin, continuous structures like noodles, causing spaghetti-like artifacts
- Repeating textures like bubbles and seeds spill beyond sensible boundaries, creating trypophobia-triggering holes
- Stylized, glossy food photography in training data is imitated without understanding context
- Models lack real-world understanding of what food should look like, causing unsettling interpretations
- Vendors
- The Verge
- Products
- AI image generators
From the original article
6 min read at theverge.com
There is a torrent of unappetizing slop coming from restaurants, cafes, and brands that are increasingly turning to AI to generate images promoting their food. The resulting horror show includes donut shrimp, Reubens from the deep, wormlike noodles, and noodle-like pastries and stringy chicken.
By Robert Hart · theverge.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.