Controllable Diverse Sampling through Pullback Directions
Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random seeds may remain visually similar, limiting creative exploration. Existing approaches can increase variation, but often require additional optimization or sampling overh...
Sylvain Dehayem Kenfouo, Aaron Zweig, Ming-Xuan Zhang et al.
· 0 citations