Research map / Video / Video generation
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei, Yuchao Gu, Yufei Shi, Wynne Hsu, Ying Shan, Xiaohu Qie, Mike Zheng Shou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| remove spatio-temporal attention (ST-Attn) (ablation) | Tune-A-Video · qualitative skier example | content consistency | Improved |
| add DDIM inversion of the input video as initial noise (ablation) | Tune-A-Video · qualitative skier example | motion fidelity | Improved |
| add one-shot finetuning of attention layers (ablation) | Tune-A-Video · qualitative skier example | temporal smoothness | Improved |
| Tune-A-Video versus Plug-and-Play frame consistency | Tune-A-Video · DAVIS 42 videos | frame consistency CLIP score: 88.89 -> 92.40 | Improved |
| Tune-A-Video versus Plug-and-Play textual alignment | Tune-A-Video · DAVIS 42 videos | textual alignment CLIP score: 27.56 -> 27.58 | No clear effect |
Later papers that compared with this method
30 later accepted papers report Tune-A-Video as a baseline in their results tables; 28 of them report a better number on most of the results they share with it.
- AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction (ICCV 2025 · better on 6 of 6 shared results)
- MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation (ICCV 2025 · better on 6 of 6 shared results)
- Spectral Motion Alignment for Video Motion Transfer Using Diffusion Models (AAAI 2025 · better on 3 of 3 shared results)
- MotionFollower: Editing Video Motion via Score-Guided Diffusion (ICCV 2025 · better on 3 of 3 shared results)
- Audio-Guided Video Scene Editing (IJCV 2025 · better on 3 of 3 shared results)
- Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consistent Video Editing (CVPR 2025 · better on 1 of 1 shared result)
- CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing (CVPR 2024 · better on 7 of 7 shared results)
- BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models (CVPR 2024 · better on 5 of 6 shared results)
22 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CogVideo — CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers (ICLR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling (ICLR 2024 · similarity 0.91)
- VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models (AAAI 2025 · similarity 0.91)
- VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide (CVPR 2025 · similarity 0.90)
- Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis (CVPR 2025 · similarity 0.90)
- FrameBridge: Improving Image-to-Video Generation with Bridge Models (ICML 2025 · similarity 0.90)
- SimDA: Simple Diffusion Adapter for Efficient Video Generation (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.
