Open-Sora (hpcaitech)

Leading#1 in Open sourcehigh confidence
The category-defining open-source video generator (~29k GitHub★) — text/image-to-video with performance comparable to HunyuanVideo on VBench.
Our read

Why it ranks #1

About 29k GitHub stars and top placement in the cited open-source model comparison make Open-Sora the highest-adoption general open video project in this track.

Here is the catch

substantial GPU requirements
setup is research-oriented rather than consumer-friendly
quality and temporal consistency trail the best closed models

Does this well

large research and contributor community
transparent training and inference stack
useful baseline for experimentation and fine-tuning

Pricing

Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.

Key features

Text and image-to-video modelsMulti-resolution and variable-duration trainingDistributed training and inferencePublished checkpoints and evaluation tooling
Search an area, or a tool by name.