Hai will present #WorldSmith today at #uist2023 at 3:02pm Pacific Time.
Join live or watch the live stream https://programs.sigchi.org/uist/2023/program/content/126668
30s video preview: https://youtube.com/watch?v=U1iF6GVbHL4
Video figure: https://youtube.com/watch?v=MBO9Uen597w
Paper: https://research.autodesk.com/publications/worldsmith/
ACM DL: https://dl.acm.org/doi/10.1145/3586183.3606772
31.10.2023 15:37Hai will present #WorldSmith today at #uist2023 at 3:02pm Pacific Time. Join live or watch the live stream...#WorldSmith conceptualizes two expressive prompting techniques for #generativeAI: hierarchical prompting (which attaches prompts to different layers of the composition) and spatial prompting (allowing users to specify spatial relations through direct input).
31.10.2023 15:36#WorldSmith conceptualizes two expressive prompting techniques for #generativeAI: hierarchical prompting (which attaches prompts to...The progress is tracked in an interactive graph, offering a dynamic way to explore and evolve their creations. 🔍🔄
31.10.2023 15:35The progress is tracked in an interactive graph, offering a dynamic way to explore and evolve their creations. 🔍🔄Images can be blended together to form one cohesive depiction of a fictional world.
31.10.2023 15:35Images can be blended together to form one cohesive depiction of a fictional world.WorldSmith is a novel UI & workflow for creators to composite scenes using iterative, multi-modal prompts for #generativeAI. 🖼️✨ It allows creators to specify their intent through text, sketching, or region-based input. 🎨
31.10.2023 15:34WorldSmith is a novel UI & workflow for creators to composite scenes using iterative, multi-modal prompts for #generativeAI. 🖼️✨...Creating images of imaginative worlds using generative AI can be a challenge to control using text-to-image alone. At #uist2023 Hai Dang will present #WorldSmith today, work we did while he was interning with us at Autodesk Research in Toronto (with @fraseranderson, George Fitzmaurice, and me).
31.10.2023 15:32Creating images of imaginative worlds using generative AI can be a challenge to control using text-to-image alone. At #uist2023 Hai Dang ...Putting it out there so I keep myself accountable: I'll be doing #AdventOfCode this year. Meant to participate for a few years, but @drmaxlwilson's Toot a few days ago reminded me of it.
1.12.2022 19:31Putting it out there so I keep myself accountable: I'll be doing #AdventOfCode this year. Meant to participate for a few years, but ...@fraseranderson has more on this as well: https://hci.social/@fraseranderson/109280873021577107
If you have any questions please get in touch with @fraseranderson, @justin_matejka, @jovermeulen, Qian Zhou, Bon Adriel Aseniero, David Ledo, or me
While attending #UIST last week I found it super valuable to re-connect with folks, but also meet new people. I especially enjoyed chatting to students (for many of whom it was their first in-person conference) on topics such as #HCI + #AI, #AR / #VR, and novel interaction techniques. We're currently looking for in-person #internships in these topics at Autodesk Research in Toronto next year. Additional topics are creativity support, software learning, and more!
https://autodesk.com/hci-vis-internship
When I click on a #hashtag here, what results are shown? Does the server that my account is on query all #mastodon instances out there to #search for toots with that hashtag? Or does it only query a subset of instances (if so, which one)? It's certainly showing results beyond just the instance I'm registered on, but I wonder how that works at scale.
7.11.2022 02:59When I click on a #hashtag here, what results are shown? Does the server that my account is on query all #mastodon instances out there to...