You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your work, this is a very interesting paper! I have a couple of question:
Does u-space contain Image Tokens + Text Tokens + Timestep? Or is u-space refereing to the input image itself (i.e. $x_t$)? Or is the u-space something completely different?
Are any pretrained models available to be downloaded? In the experiments you mentioned that you used a pretrained latent
flow-matching model on MS COCO. Is this model publicly available?
The text was updated successfully, but these errors were encountered:
Hi,
Thank you for your work, this is a very interesting paper! I have a couple of question:
flow-matching model on MS COCO. Is this model publicly available?
The text was updated successfully, but these errors were encountered: