Improved Distributional Diffusion Models
A stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation.
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
A stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation.
This work introduces a promptable localized motion representation that produces persistent embeddings for user-specified regions defined by spatial masks that improves controllability and outperforms global representations localized through cropping or post-hoc masking.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.