Conditional Gradient-based Textual Inversion
Résumé
Generative models excel in image generation but often require trail-and-errors for specific concepts. Textual inversion offers a solution; yet, is computationally costly. We propose using conditional gradient data to select or sample informative timesteps for textual inversion. Our methods improve computational cost and generation quality.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|