showlab/Show-1

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1148 stars · 59 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Show-1 is a research codebase implementing a text-to-video generation model that combines pixel and latent diffusion models, published at IJCV by Show Lab, NUS. It provides inference scripts and pretrained weights (base, interpolation, and super-resolution stages) for generating short videos from text prompts.

Use cases

• generate videos from text prompts
• run text-to-video diffusion model inference
• research pixel and latent diffusion for video generation
• reproduce IJCV paper results
• super-resolve and interpolate generated video frames
• try a text-to-video model on GPU or Colab

When to choose

• you want to generate short videos from text descriptions
• you are researching hybrid pixel/latent diffusion architectures
• you need a published, paper-backed text-to-video baseline
• you want pretrained text-to-video weights on HuggingFace

When to avoid

• you need production-grade, fast video generation
• you lack a capable GPU
• you need permissively licensed code for commercial use
• you want actively developed features or long-form video output

Facets

library · maturity maintenance

deep-learning machine-learning video-processing stable-diffusion llm-inference deep-learning machine-learning artificial-intelligence image-processing python text-to-video diffusion-models video-generation generative-ai research-code pixel-diffusion latent-diffusion video gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="showlab/Show-1")