Research map / Video / Video generation
Kinetic Typography Diffusion Model
Seonmi Park, Inhwan Bae, Seunghyun Shin, Hae-Gon Jeon
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 |
|---|---|---|---|
| separate static and dynamic captions into spatial and temporal attention (ablation) | KineTy · KineTy eval (average) | FVD: 729.8 -> 125.90 | Improved |
| add word caption branch with zero convolution (ablation) | KineTy · KineTy eval (average) | FVD: 201.8 -> 125.90 | Improved |
| add word caption branch with zero convolution (ablation) | KineTy · KineTy eval (average) | OCR F1: 0.74 -> 0.76 | Improved |
| add glyph loss (ablation) | KineTy · KineTy eval (average) | FVD: 160.8 -> 125.90 | Improved |
| add glyph loss (ablation) | KineTy · KineTy eval (average) | OCR F1: 0.75 -> 0.76 | No clear effect |
| end-to-end KineTy vs two-stage text-to-image plus SparseCtrl on text legibility | KineTy · KineTy eval (average) | OCR F1: 0.90 -> 0.76 | Hurt |
| use KineTy instead of general text-to-video models | video diffusion baselines · KineTy eval (average) | FVD: 956.97 -> 125.90 | Improved |
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.
- Lavie — LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models (IJCV 2024) · better on 4 of 4 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
- Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model (AAAI 2024 · similarity 0.86)
- Layout-Agnostic Scene Text Image Synthesis with Diffusion Models (CVPR 2024 · similarity 0.85)
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning (ICLR 2024 · similarity 0.85)
- MotiF: Making Text Count in Image Animation with Motion Focal Loss (CVPR 2025 · similarity 0.85)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.84)
- Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer (CVPR 2024 · similarity 0.84)
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.
