How would you generate prompts for a relatively coherent metaverse of dalle2 objects?
Eg: maybe your theme is “fruits and vegetables” and you do stuff like:
Tomato office building
Root vegetables highway
Strawberry dungeon
This is clearly a new kind of job. Wonderland Conjurer
Conversation
Replying to
I’d be curious to see if it understands perspective enough to generate images of the same scene from different angles. Could eventually try to turn those into 3D models.
1
1
Replying to
That doesn’t sound like a significant extra step. You wouldn’t use GPT though… probably just trad GOFAI and 3D algorithms. I can imagine rotating the wireframe from one perspective and getting GPT to fill in the missing details.
1
Show replies
Replying to
Why make humans do the inbetween work? If "fruit and vegetable land" is your prompt, let it run with that. The human storyteller only needs to intervene when they have a particular *something* they want to convey.
1
1
Replying to
You need to populate a whole interesting metaverse world, not just a surreal fruit and veggies landscape
1
1
Show replies
Replying to
There are definitely going to be some weird worlds to explore, as well as many unnecessary graphic novels.
2
Replying to
People do this today in the form of creating a vision or design language which then human artists develop into real worlds.
2
Replying to
But then how could we pretend that blockchains are an important part of metaverse asset management








