Research map / Video / Video generation
Video Diffusion Models
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 |
|---|---|---|---|
| add 8 independent image frames per video (joint image-video training) (ablation) | text-to-video diffusion · Text-to-video 16x64x64 | FVD: 202.28 -> 57.84 | Helped |
| increase classifier-free guidance weight 1.0 -> 5.0 (ablation) | text-to-video diffusion · Text-to-video frameskip 1 | IS-avg: 10.80 -> 14.80 | Helped |
| increase classifier-free guidance weight 1.0 -> 5.0 (ablation) | text-to-video diffusion · Text-to-video frameskip 1 | FVD: 41.65 -> 163.74 | Hurt |
| reconstruction guidance instead of replacement for conditioning (ablation) | autoregressive extension · 64x64x64 generation | FVD: 451.45 -> 136.22 | Helped |
| Langevin sampler instead of ancestral (ablation) | Video Diffusion · Kinetics-600 | FVD: 18.6 -> 16.2 | Helped |
| video diffusion vs prior GAN/AR methods | video generation · BAIR Robot Pushing | FVD: 86.9 -> 66.92 | Helped |
Closest papers by meaning
- Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition (ICLR 2024 · similarity 0.92)
- Grid Diffusion Models for Text-to-Video Generation (CVPR 2024 · similarity 0.92)
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CVPR 2025 · similarity 0.92)
- AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion (CVPR 2025 · similarity 0.92)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.91)
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention (NeurIPS 2024 · similarity 0.91)
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.