Train an unconditional LDM on different classes, is it ok?
#222
by
Vincent171
- opened
Hi, I see that all pre-trained unconditional LDMs are trained on just one class such as "flowers", "landscape",... Therefore, they can only generate images related to one specific class (e.g., generating different flowers, but still flowers, not a car or a dog).
If we train an unconditional LDM on images of different datasets that include various classes, could the model generate something cool? Depending on the random seed, maybe sometimes it generate a flower, but sometimes a dog?