« Dreambooth » : différence entre les versions
Aller à la navigation
Aller à la recherche
(Page créée avec « Dreambooth is a kind of fine-tuning that attempts to introduce new subjects by providing just a few images of the new subject. The goal is similar to that of Textual Inversion, but the process is different. Instead of creating a new token as Textual Inversion does, we select an existing token in the vocabulary (usually a rarely used one), and fine-tune the model for a few hundred steps to bring that token close to the images we provide. This is a regular fine-tun... ») |
(Aucune différence)
|
Version actuelle datée du 5 janvier 2023 à 13:54
Dreambooth is a kind of fine-tuning that attempts to introduce new subjects by providing just a few images of the new subject. The goal is similar to that of Textual Inversion, but the process is different. Instead of creating a new token as Textual Inversion does, we select an existing token in the vocabulary (usually a rarely used one), and fine-tune the model for a few hundred steps to bring that token close to the images we provide. This is a regular fine-tuning process in which all modules are unfrozen.