Justin Johnson
@jcjohnss
Latent Forcing lets us train strong pixel-space diffusion models that benefit from DINOv2 alignment like many recent latent diffusion models.
But it's a lot more than that -- it's also a new way to approach coarse-to-fine generation and latent "chain-of-thought" reasoning for
But it's a lot more than that -- it's also a new way to approach coarse-to-fine generation and latent "chain-of-thought" reasoning for
Alan Baade@BaadeAlan · Feb 17What's the right space to diffuse in: Raw Data or Latents?
Why not both!
In Latent Forcing, we order a joint diffusion trajectory to reveal Latents before Pixels, leading to improved convergence while being lossless at encoding and end-to-end at inference.
w/ @drfeifei+...
1/n
Why not both!
In Latent Forcing, we order a joint diffusion trajectory to reveal Latents before Pixels, leading to improved convergence while being lossless at encoding and end-to-end at inference.
w/ @drfeifei+...
1/n
Open quoted post →
1 140