PKU-YuanGroup/Open-Sora-Plan

Health v2 · maintenance only

Adoption not part of the score

12155 stars · 1060 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Open-Sora Plan is an open-source effort to reproduce OpenAI's Sora text-to-video model, providing training and inference code for video generation models including a WF-VAE and DiT-based architectures. It is developed by the PKU-Yuan Group with community contributions and supports training on Ascend NPUs.

Use cases

• generate videos from text prompts
• train a text-to-video diffusion model
• reproduce Sora-style video generation
• run open-source video generation inference
• fine-tune a video generation model on custom data
• research video generation architectures like VAE and DiT

When to choose

• you need an open-source, self-hosted text-to-video model you can inspect and modify
• you want to train or fine-tune video generation models on your own hardware including Ascend NPUs
• you are doing research on video diffusion architectures

When to avoid

• you need a polished production-ready video generation service with minimal setup
• you lack significant GPU/NPU resources, since training is compute-intensive
• you only need simple image generation rather than video

Facets

library · maturity active

deep-learning machine-learning video-processing llm-training deep-learning artificial-intelligence image-processing python text-to-video video-generation diffusion-models sora-reproduction open-source-model vae transformers video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PKU-YuanGroup/Open-Sora-Plan")