Vchitect/Latte
Some data may be outdated — see provenance labels.
[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation. observed · 2026-10-02
Health v2 · maintenance only
68/100
- Activity 89
- Release rhythm 35
- Longevity 77
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 1088
- days_rel: n/a
- days_push: 71
- n_releases_24m: 0
Adoption not part of the score
1948 stars · 190 forks observed · 2026-10-02
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Official PyTorch implementation of Latte, a latent diffusion transformer for video generation. It includes model definitions, pre-trained checkpoints, and training/sampling/evaluation code for text-to-video synthesis.
Use cases
- generate videos from text prompts
- train a diffusion transformer on video data
- sample videos from pre-trained checkpoints
- research video generation models
- evaluate video generation quality
When to choose
- you need a research-grade text-to-video diffusion model with open weights
- you want to experiment with latent diffusion transformer architectures for video
When to avoid
- you need production-ready, optimized video generation inference
- you lack GPU resources for large diffusion models
Facets
library · maturity active
deep-learning video-processing machine-learning deep-learning python diffusion-transformer text-to-video video-generation pytorch research-code video gpu
1 source
- readme: https://github.com/Vchitect/Latte · fetched 2026-10-02 · d6273834bf53
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| Vchitect/Latte | main | 68 |
For agents
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem