Make-A-Video: Text-to-Video Generation without Text-Video Data
GPTKB entity
Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:academic_journal
|
| gptkbp:arXivID |
2211.02495
|
| gptkbp:author |
Hubert, Thomas
Dekel, Tali Hasson, Yossi Rubinstein, Michael Shaham, Tamar Shalev, Shai Wolf, Lior |
| gptkbp:compatibleWith |
paired text-video data
|
| gptkbp:demonstrates |
video synthesis from text prompts
|
| gptkbp:describes |
text-to-video generation
|
| gptkbp:field |
gptkb:artificial_intelligence
computer vision generative models |
| gptkbp:proposedBy |
method for generating videos from text prompts
|
| gptkbp:publicationYear |
2022
|
| gptkbp:publishedBy |
gptkb:Meta_AI
|
| gptkbp:url |
https://arxiv.org/abs/2211.02495
|
| gptkbp:uses |
pre-trained text-image models
|
| gptkbp:bfsParent |
gptkb:Make-A-Video
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Make-A-Video: Text-to-Video Generation without Text-Video Data
|