Papers › Make-A-Video: Text-to-Video Generation without Text-Video Data
Make-A-Video: Text-to-Video Generation without Text-Video Data
Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, Yaniv Taigman
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text-to-Video Generation | MSR-VTT | Make-A-Video | CLIP-FID | 13.17 | #12 of 18 | Archive leaderboard | report |
| Text-to-Video Generation | MSR-VTT | Make-A-Video | CLIPSIM | 0.3049 | #12 of 18 | Archive leaderboard | report |
| Text-to-Video Generation | MSR-VTT | Make-A-Video | FID | 13.17 | #12 of 18 | Archive leaderboard | report |
| Text-to-Video Generation | MSR-VTT | CogVideo (English) | CLIP-FID | 23.59 | #15 of 18 | Archive leaderboard | report |
| Text-to-Video Generation | MSR-VTT | CogVideo (English) | CLIPSIM | 0.2631 | #15 of 18 | Archive leaderboard | report |
| Text-to-Video Generation | MSR-VTT | CogVideo (English) | FID | 23.59 | #15 of 18 | Archive leaderboard | report |
| Video Generation | UCF-101 | Make-A-Video (Finetuning, 256x256, class-conditional) | FVD16 | 81.25 | #8 of 48 | Archive leaderboard | report |
| Video Generation | UCF-101 | Make-A-Video (Finetuning, 256x256, class-conditional) | Inception Score | 82.55 | #8 of 48 | Archive leaderboard | report |
| Video Generation | UCF-101 | Make-A-Video (Zero-shot, 256x256, class-conditional) | FVD16 | 367.23 | #31 of 48 | Archive leaderboard | report |
| Video Generation | UCF-101 | Make-A-Video (Zero-shot, 256x256, class-conditional) | Inception Score | 33 | #31 of 48 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections