Skip to main content

Log in to comment and vote

Comments35

  • Tomato Melon

    •

    Jan 21, 2025

    I would love this feature! Currently have two AI subscription. I'd be able to get all my workflows done with this one.

  • Indigo Straw

    •

    Feb 9, 2025

    We have a working prototype of this — hoping to make a beta release of it next week.

  • Yellow Nucleon

    •

    Jan 28, 2025

    Text extraction from the image would be cool too

  • Ivory Gravy

    •

    Feb 1, 2025

    Please add image upload support would literally knock out so many other AIs.

  • Cyan Drizzle

    •

    Feb 7, 2025

    The Only thing stopping me from switching from ChatGPT to Venice is because of this. If you can Implement this I will 100% be switching over and imagine it would be much more appealing to others as well.

  • Plum Thimble

    •

    Feb 26, 2025

    Does anyone know how to use this feature via the API?

    • Teal Dew

      •

      Feb 27, 2025

      I have used it in a tool for extracting receipts. I am using the model to recognize receipts on a image, provide boundary box coordinates so I can then extract the receipts from the image. https://github.com/tbystrican/receipt-extraction-tool

  • Pink Moss

    •

    Oct 27, 2025

    What is my skin color and guess my ethnicity

  • Silver River

    •

    Jan 28, 2025

    Would be helpful to describe scenes and characters in a way that a generative model could understand when prompting for the same or similar.

  • Cyan Pea

    •

    Jan 28, 2025

    the interface seems dark, some people prefer light interface

    • Chocolate Antelope

      •

      Jan 30, 2025

      This is customizable from the settings selector in the top right corner of the UI.

  • Amethyst Horse

    •

    Jan 31, 2025

    Please add this!