Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

723
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

Fahim Farook

"Guiding Text-to-Image Diffusion Model Towards Grounded Generation. (arXiv:2301.05221v1 [cs.CV])" — Enhance a pre-trained text-to-image diffusion model to simultaneously generate images and segmentation masks for the corresponding visual entities described in the text prompt.

Paper: arxiv.org/abs/2301.05221
Code: No code in linked repo (yet)

<<Find this useful? Please boost so that others can benefit too 🙂>>

Predictions from our guided text-to-image diffusion model. The model is able to simultaneously generate images and segmentation masks for the corresponding visual objects described in the text prompt, for example, Pikachu, Unicorn, Phoenix, etc.
Jan 13, 2023, 03:47 AM·Public·Web
3boosts·3favorites
ExploreLive feeds
About