“Prompt to Anything?: Exploring Generative AI’s Iterative Potential in Mapping Show Production” by Borgomano – ACM SIGGRAPH HISTORY ARCHIVES

“Prompt to Anything?: Exploring Generative AI’s Iterative Potential in Mapping Show Production” by Borgomano

  • ©

Conference:


Type(s):


Title:

    Prompt to Anything?: Exploring Generative AI's Iterative Potential in Mapping Show Production

Session/Category Title:   Generative AI and Style Transfer


Presenter(s)/Author(s):



Abstract:


    “Prompt to Anything?” highlights Moment Factory’s exploration with Generative AI (Gen-AI) in enhancing location-based experiences and 3D mapping shows. This talk will outline our innovation journey from concept to execution, demonstrating Gen-AI’s integration possibilities into large-scale projects, and sharing key insights and achievements, encouraging further creative investigations with Gen-AI.

References:


    [1]
    AUTOMATIC1111. 2022. Stable Diffusion Web-UI. https://github.com/AUTOMATIC1111/stable-diffusion-webui. Accessed: July 19, 2023.
    [2]
    Comfyanonymous. 2022. ComfyUI: A Web Interface for Stable Diffusion. https://github.com/comfyanonymous/ComfyUI. Accessed: July 19, 2023.
    [3]
    Coyote-A. 2023. Ultimate SD Upscale extension for AUTOMATIC1111 Stable Diffusion web UI. https://github.com/Coyote-A/ultimate-upscale-for-automatic1111. Accessed: July 19, 2023.
    [4]
    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv:2112.10752 [cs.CV]
    [5]
    Bounding Box Software. 2018. Materialize. Bounding Box Software. https://boundingboxsoftware.com/materialize/index.php
    [6]
    Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org