https://www.infoq.com InfoQ Stability Diffusion News feed https://www.infoq.com/news/2025/07/diffusion-model-creativity/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Stability+Diffusion-news <img src="https://res.infoq.com/news/2025/07/diffusion-model-creativity/en/headerimage/diffusion-models-creativity-1751814254644.jpeg"/><p>In a recent paper, Stanford researchers Mason Kamb and Surya Ganguli proposed a mechanism that could underlie the creativity of diffusion models. The mathematical model they developed suggests that this creativity is a deterministic consequence of how those models use the denoising process to generate images.</p> <i>By Sergio De Simone</i> Generative AI Neural Networks Stability Diffusion AI, ML & Data Engineering news Sun, 06 Jul 2025 16:00:00 GMT https://www.infoq.com/news/2025/07/diffusion-model-creativity/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Stability+Diffusion-news Sergio De Simone 2025-07-06T16:00:00Z /news/2025/07/diffusion-model-creativity/en