Show-1
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- National University of Singapore
- Organisation type
- Academia
- Country
- Singapore
- Published
- 27 September 2023
- Authors
- David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, Mike Zheng Shou
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video
- Task
- Video generation, Text-to-video
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- 160,358,400,000,000 tokens
WebVid-10M 10.7M video-caption pairs. 52K total video hours.
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (non-commercial)
- Training code
- Unreleased
https://github.com/showlab/Show-1 don't see training code Attribution-NonCommercial 4.0 International
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
"Our approach achieves state-of-the-art performance on standard benchmarks including UCF-101 and MSR-VTT."
Sources
Where this record came from and when it was last checked.
- Reference
- Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Show-1 was published by National University of Singapore, in Singapore, in September 2023. academia is the category the publisher falls under.
It works in Video, and is recorded as doing video generation, Text-to-video.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
Training and provenance
It was trained on about 160,358,400,000,000 tokens of text.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
Show-1 — common questions
What is Show-1 used for?
Show-1 works in Video, and is recorded as handling video generation, Text-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Show-1?
The weights for Show-1 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run Show-1?
We cannot say. Show-1 has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is Show-1 open source?
Its weights are published, so Show-1 can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does Show-1 have?
No parameter count has been published for Show-1, which is why no memory or speed figure appears on this page.
Who created Show-1?
Show-1 was published by National University of Singapore, based in Singapore, categorised as academia.
When was Show-1 released?
Show-1 was published in September 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.