Research map / Video / Video generation
Make-A-Video: Text-to-Video Generation without Text-Video Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Make-A-Video instead of CogVideo (English) | zero-shot text-to-video generation · MSR-VTT | FID: 23.59 -> 13.17 | Helped |
| Use Make-A-Video instead of CogVideo (English) | zero-shot text-to-video generation · MSR-VTT | CLIPSIM: 0.2631 -> 0.3049 | Helped |
| Use Make-A-Video instead of CogVideo (English) | zero-shot video generation · UCF-101 zero-shot | IS: 25.27 -> 33.00 | Helped |
| Use Make-A-Video instead of CogVideo (English) | zero-shot video generation · UCF-101 zero-shot | FVD: 701.59 -> 367.23 | Helped |
| Use Make-A-Video instead of TATS-base | fine-tuned video generation · UCF-101 fine-tuning | IS: 79.28±0.38 -> 82.55 | Helped |
| Use Make-A-Video instead of TATS-base | fine-tuned video generation · UCF-101 fine-tuning | FVD: 278±11 -> 81.25 | Helped |
| Use Make-A-Video instead of VDM | text-to-video generation · VDM prompts (28) | human preference for quality: 84.38 | Helped |
| Use Make-A-Video instead of VDM | text-to-video generation · VDM prompts (28) | human preference for faithfulness: 78.13 | Helped |
| Use Make-A-Video instead of CogVideo (English) | text-to-video generation · DrawBench (200) | human preference for quality: 74.48 | Helped |
| Use Make-A-Video instead of CogVideo (English) | text-to-video generation · DrawBench (200) | human preference for faithfulness: 68.75 | Helped |
| Use Make-A-Video interpolation instead of FILM | frame interpolation · Our evaluation set and DrawBench | human preference for realistic motion: 62%; 54% | Helped |
Closest papers by meaning
- A Recipe for Scaling up Text-to-Video Generation with Text-free Videos (CVPR 2024 · similarity 0.92)
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.91)
- VideoTetris: Towards Compositional Text-to-Video Generation (NeurIPS 2024 · similarity 0.90)
- OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation (ICLR 2025 · similarity 0.90)
- LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity (CVPR 2025 · similarity 0.90)
- Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis (CVPR 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.