The idea is that, you know, the output image has a lot of this sort of colors or the, or the sort of structures, the positions, very similar to that original sketch. And we are then, of course, taking our diffusion model, which is given the semantic information coming from our clip embeddings, and it is producing a nice final result That matches the sort of maybe colors or the spatial positions structures that was there in their originalVery blurry kind of sketch of the image that was produced by our low level pipeline. But again, I mean, it just helps a bit. It helps a bit and gives you better low level information, better low level results.

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