Research map / Video / Video generation
Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
David Junhao Zhang, Jay Zhangjie Wu, Jiawei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, 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 |
|---|---|---|---|
| use pixel-based instead of latent (f=8) VDM for 64x40 keyframes (ablation) | Show-1 · Keyframe stage ablation | CLIPSIM: 0.2441 -> 0.3096 | Improved |
| use pixel-based instead of latent (f=8) VDM for 64x40 keyframes (ablation) | Show-1 · UCF-101 | FVD: 584 -> 383 | Improved |
| generate low-resolution 64x40 keyframes instead of high-resolution 512x320 with latent VDM (f=8) (ablation) | Show-1 · Keyframe stage ablation | CLIPSIM: 0.2793 -> 0.3096 | Improved |
| use latent final super-resolution instead of pixel final super-resolution (ablation) | Show-1 · Inference memory | max memory: 72GB -> 15GB | Improved |
| lower latent compression ratio (f=8 -> f=2) at 64x40 keyframes (ablation) | latent keyframe VDM · Keyframe stage ablation | CLIPSIM: 0.2441 -> 0.2742 | Improved |
| increase resolution of latent keyframes from 256x160 to 512x320 (f=8) (ablation) | latent keyframe VDM · Keyframe stage ablation | CLIPSIM: 0.2874 -> 0.2793 | Hurt |
| change input to noised-denoised (SDEdit) low-res video in final super-resolution (ablation) | SDx4 with temporal layers · UCF-101 | FVD: 459 -> 423 | Improved |
| add expert finetuning (timesteps 0-900) to expert translation (ablation) | Final super-resolution module · UCF-101 | FVD: 423 -> 383 | Improved |
| add expert finetuning (timesteps 0-900) to expert translation (ablation) | Final super-resolution module · UCF-101 | IS: 33.83 -> 35.67 | Improved |
| finetune whole pipeline on square videos instead of resizing outputs | Show-1 · UCF-101 | FVD: 383.46 -> 369.33 | Improved |
| use Show-1 hybrid pipeline instead of reproduced Make-A-Video | Show-1 · Inference speed | total time: 256s -> 178s | Improved |
| use Show-1 latent final super-res instead of Make-A-Video pixel final super-res | Show-1 · Inference memory | final SR memory: 54GB -> 15GB | Improved |
Later papers that compared with this method
5 later accepted papers report Show-1 as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents (ICCV 2025 · better on 1 of 1 shared result)
- Unified Video Generation via Next-Set Prediction in Continuous Domain (ICCV 2025 · better on 1 of 1 shared result)
- VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models (CVPR 2024 · better on 4 of 4 shared results)
- VideoPoet: A Large Language Model for Zero-Shot Video Generation (ICML 2024 · better on 2 of 2 shared results)
- Grid Diffusion Models for Text-to-Video Generation (CVPR 2024 · better on 1 of 1 shared result)
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.
- Make-A-Video — Make-A-Video: Text-to-Video Generation without Text-Video Data (ICLR 2023) · better on 3 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
- Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search (NeurIPS 2025 · similarity 0.90)
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer (ICLR 2025 · similarity 0.89)
- MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance (AAAI 2024 · similarity 0.89)
- LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity (CVPR 2025 · similarity 0.89)
- VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide (CVPR 2025 · similarity 0.89)
- EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation (CVPR 2025 · similarity 0.89)
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.
