#2222nd of 24 in Image and videoFor image, video and design, video and animation
open-sora-plan
Open text-to-video diffusion models and training code, reproducing Sora
- Stars
- 12.2k
- License
- MIT
- Last commit
- Mar 2026
- Last release
- Jun 2025
- Language
- Python
12,037 on 31 Mar 202612,207 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Open-Sora Plan releases text-to-video and image-to-video diffusion transformer checkpoints (v1.0.0 to v1.5.0) along with the WF-VAE video autoencoder and a prompt refiner. Version 1.5.0 uses an 8B sparse DiT (SUV) and an 8x8x8 WF-VAE, and is trained and run on Ascend 910 NPUs via the MindSpeed-MM branch. The GPU version is listed as coming soon.
Who it is for: Researchers running open video diffusion models, esp. on Ascend NPUs
Strengths
- Weights published for every version v1.0.0 through v1.5.0 on Hugging Face
- v1.3.0 supports 93x480p generation within 24G VRAM
- WF-VAE with 8x8x8 downsampling; README claims higher PSNR than the Wan2.1 VAE
- Includes image-to-video checkpoints, a prompt refiner, and technical reports per version
Weaknesses
- v1.5.0 weights only work with NPU plus MindSpeed-MM; GPU instructions say coming soon
- Main branch has no runnable setup; code lives on the mindspeed_mmdit branch
- No Docker, web UI or hosted demo; research-style checkpoints only
- README license badge says Apache while detected license is MIT
What it needs
- GPU required
- Needs Ascend 910 NPU (v1.5.0), MindSpeed-MM
- Models: Text-to-video, Image-to-video, WF-VAE, SUV sparse DiT
Also in Image and video
See all 24| Rank | Project | Score |
|---|---|---|
| 1 | MoneyPrinterTurboTurns a topic into a short video with script, footage, voiceover and subtitles | 76 out of 100 |
| 2 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 75 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 69 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 67 out of 100 |
| #5 | open-generative-aiImage, video and lip-sync studio UI that calls MuAPI, with optional local engines | 64 out of 100 |