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
Hi, We use Chameleon model weights as initialization and unlock the full model for fine-tuning (including token embeddings and logit projection head). It is also proven by some projects like lumina-mgpt and anole that simple finetuning can fully unlock its image generation ability.
Dear authors,
The currently released Chameleon models do not seem to support image generation. Which exact models were your using for this project?
Thanks!
The text was updated successfully, but these errors were encountered: