Ars Technica

Better than JPEG? Researcher discovers that Stable Diffusion can compress images

Last week, Swiss software engineer Matthias Bühlmann discovered that the popular image synthesis model Stable Diffusion could compress existing bitmapped images with fewer visual artifacts than JPEG ...
MIT Technology Review

Text-to-image AI models can be tricked into generating disturbing images

Nonsense words can trick Stable Diffusion and DALL-E 2 into producing pictures that show violence and nudity. Popular text-to-image AI models can be prompted to ignore their safety filters and ...
Digi Times

DeepSeek unveils optical compression model to enhance long text processing for AI

Chinese artificial intelligence startup DeepSeek has introduced DeepSeek-OCR, an open-source model accompanied by a research paper that pioneers a novel "optical compression" method aimed at reducing ...
MIT Technology Review

DeepSeek may have found a new way to improve AI’s ability to remember

Instead of using text tokens, the Chinese AI company is packing information into images. An AI model released by the Chinese AI company DeepSeek uses new techniques that could significantly improve AI ...

Open-source image generator startup Black Forest Labs raises $300M

Black Forest Labs Inc., a startup that develops artificial intelligence models optimized for image generation tasks, has ...