Video Editing via Factorized Diffusion Distillation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917621441495040 |
|---|---|
| author | Singer, Uriel Zohar, Amit Kirstain, Yuval Sheynin, Shelly Polyak, Adam Parikh, Devi Taigman, Yaniv |
| author_facet | Singer, Uriel Zohar, Amit Kirstain, Yuval Sheynin, Shelly Polyak, Adam Parikh, Devi Taigman, Yaniv |
| contents | We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing adapter and a video generation adapter, and attach both to the same text-to-image model. Then, to align the adapters towards video editing we introduce a new unsupervised distillation procedure, Factorized Diffusion Distillation. This procedure distills knowledge from one or more teachers simultaneously, without any supervised data. We utilize this procedure to teach EVE to edit videos by jointly distilling knowledge to (i) precisely edit each individual frame from the image editing adapter, and (ii) ensure temporal consistency among the edited frames using the video generation adapter. Finally, to demonstrate the potential of our approach in unlocking other capabilities, we align additional combinations of adapters |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09334 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Video Editing via Factorized Diffusion Distillation Singer, Uriel Zohar, Amit Kirstain, Yuval Sheynin, Shelly Polyak, Adam Parikh, Devi Taigman, Yaniv Computer Vision and Pattern Recognition We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing adapter and a video generation adapter, and attach both to the same text-to-image model. Then, to align the adapters towards video editing we introduce a new unsupervised distillation procedure, Factorized Diffusion Distillation. This procedure distills knowledge from one or more teachers simultaneously, without any supervised data. We utilize this procedure to teach EVE to edit videos by jointly distilling knowledge to (i) precisely edit each individual frame from the image editing adapter, and (ii) ensure temporal consistency among the edited frames using the video generation adapter. Finally, to demonstrate the potential of our approach in unlocking other capabilities, we align additional combinations of adapters |
| title | Video Editing via Factorized Diffusion Distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.09334 |