TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

108 points by 037 5 months ago | 23 comments
  • jasonjmcghee 5 months ago
    Feels like a moodboarding multiplier for some design disciplines, if these aren't cherry-picked / transfer to other domains.

    Pretty interesting.

    Seems like you could apply similar ideas to text too.

    • test6554 5 months ago
      Something like this could make creatives feel more in control and less averse to AI image generation.
      • mettamage 5 months ago
        Not just a moodboard if you can highlight the words you want in your output.
      • sdenton4 5 months ago
        This looks like an excellent step towards being able to apply consistency to generated images across a series.
        • basch 5 months ago
          It looks as if it would trivially integrate into Whisk, which already has a similar feature for defining an outputs “subjects” “scene” and “style”.
        • jiggawatts 5 months ago
          “Code coming soon” from Google means basically never.

          I don’t understand why they keep making these announcements and then just sitting on the results.

          This is an immediately commercially useful product even as an API. You could make a mobile app for kids to “create their own cartoon story”.

          Someone else will have to reproduce this for it to see the light of day.

          • wildermuthn 5 months ago
            We might eventually see the code for the models and inference, but I do doubt we’ll see training code or be granted access to training data. Google is pretty bad at this.
            • Kiro 5 months ago
              I have the same feeling but I wonder if it's actually true. Do we have any examples of announcements where the code was never released?
            • eichi 4 months ago
              Any update?
              • HenryBemis 5 months ago
                My eyes are so tired... I read it as "TolkienVerse" (wishful thinking took over actual letters I guess) and I thought WOW!!!!! that is amazing!!!! When I clicked and saw "a dog wearing a hat".. uff...
                • eichi 5 months ago
                  Seems good tool for automated PowerPoint generation but I believe the content is much more important.

                  So why not automate the attachment of images to concentrate on the more important tasks? I hope the code will be available soon!

                  • PoignardAzur 5 months ago
                    Looks like it lets you transfer textures, poses, and general "vibe of object" stuff, but still doesn't let you control composition.

                    Overall the example images still look like overly corporate slop.

                    • ziofill 5 months ago
                      Storytelling with characters is a huge selling point
                      • doctorpangloss 5 months ago
                        If it worked with people, they’d show people.
                        • SeanAnderson 5 months ago
                          The second example in the "Results" section includes a human.
                          • doctorpangloss 5 months ago
                            They do not show a realistic photo face transfer. They blur out the faces even.

                            It would be a huge invention, but they did not achieve that.

                            • drewbeck 5 months ago
                              Below the first Results header is a carousel of images. If you tap the arrows you can explore — I believe there are three examples where the final image is a person who’s face was applied from a reference photo.