Is the next thing going to be image generation trained on your own photos? It seems like personalized generation would be a huge market.
Ex. Show me walking on a beach. Show my dog wearing sunglasses, etc.
Ex. Show me walking on a beach. Show my dog wearing sunglasses, etc.
https://textual-inversion.github.io/
It allows you to find a string that corresponds to some "thing" you have pictures of. Then you can use a text to image model containing a reference to your "thing".
Looks pretty amazing! However it needs 20gb of VRAM so I couldn't try it out.