Skip navigation
MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable…
0:00 / 0:23

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable…

Yasutaka Furukawa

@YasutakaFuruka12.5K followers

Visit on X
189 likesDownloadOriginal post

33,484 views

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

8 Comments

Comments from the original post on X (Twitter)

  • Yasutaka Furukawa's profile picture

    @YasutakaFuruka1

    I am very sorry. Typo fixing. Had to delete the old one and retweet.

  • Yasutaka Furukawa's profile picture

    @YasutakaFuruka1

    I had to delete and repost. Highly appreciate it if you could reshare/retweet this post

    1 like

  • Ziyu Wan's profile picture

    @raywzy1

    Awesome work!!!!! I wonder where we could find the paper😊

    1 like

  • Yasutaka Furukawa's profile picture

    @YasutakaFuruka1

    Thank you Ziyu. Did not realize that we haven't uploaded to arxiv yet... Asking students to upload in a day.

    1 like

  • Jake Harrison's profile picture

    @AIDailyGuy

    I would add to my newsletter

    1 like

  • Philipp Tsipman's profile picture

    @ptsi

    🔥

  • Asriel H's profile picture

    @asrlhhh

    does it support image prompt as input or only text prompt?

  • Yasutaka Furukawa's profile picture

    @YasutakaFuruka1

    Only text for this work. But it seems trivial to add image-prompt capability.