Research map / Video / Video generation
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
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 |
|---|---|---|---|
| add motion dynamics to initial latent codes (ablation) | Text2Video-Zero · Qualitative temporal consistency (text-to-video, ControlNet edge) | temporal consistency (qualitative) | Improved |
| add cross-frame attention on first frame instead of self-attention (ablation) | Text2Video-Zero · Qualitative identity preservation | object identity/appearance preservation (qualitative) | Improved |
| combine motion latents with cross-frame attention (ablation) | Text2Video-Zero · Qualitative temporal coherence | temporal coherence (qualitative) | Improved |
| apply motion at T' < T (Delta t = 60) instead of Delta t = 0 (ablation) | Text2Video-Zero · Qualitative object motion | object motion (qualitative) | Improved |
| add background smoothing (alpha=0.6) (ablation) | Text2Video-Zero · Qualitative background consistency | background consistency (qualitative) | Improved |
| replace per-frame Instruct-Pix2Pix with cross-frame attention version | Video Instruct-Pix2Pix · Video editing consistency | temporal consistency (qualitative) | Improved |
| apply method on top of ControlNet | ControlNet · Conditional video generation | temporal consistency (qualitative) | Improved |
Later papers that compared with this method
12 later accepted papers report Text2Video-Zero as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation (ECCV 2026 · better on 1 of 1 shared result)
- MotionCraft: Physics-Based Zero-Shot Video Generation (NeurIPS 2024 · better on 8 of 10 shared results)
- ConditionVideo: Training-Free Condition-Guided Video Generation (AAAI 2024 · better on 7 of 7 shared results)
- CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing (CVPR 2024 · better on 5 of 5 shared results)
- CCEdit: Creative and Controllable Video Editing via Diffusion Models (CVPR 2024 · better on 4 of 4 shared results)
- ControlVideo: Training-free Controllable Text-to-video Generation (ICLR 2024 · better on 4 of 4 shared results)
- Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation (CVPR 2024 · better on 3 of 3 shared results)
- A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing (CVPR 2024 · better on 1 of 2 shared results)
4 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 1 of 1 shared result
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
- TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models (CVPR 2024 · similarity 0.92)
- EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation (CVPR 2025 · similarity 0.92)
- ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models (CVPR 2025 · similarity 0.91)
- A Recipe for Scaling up Text-to-Video Generation with Text-free Videos (CVPR 2024 · similarity 0.91)
- ControlVideo: Training-free Controllable Text-to-video Generation (ICLR 2024 · similarity 0.91)
- Grid Diffusion Models for Text-to-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.
