Stable attribution is a way to figure out how images in stable diffusion's training set influence particular generations that are created. The reason we took this approach is again, because there are optimal approaches, but they are all computationally intractable. Every training run of stable diffusion costs about 160 grand. So it's computationally infeasible. We found a different approach we think it's principled.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode