Wan (Alibaba, Wan2.2)
Leading#2 in Open sourcehigh confidence
Alibaba's Wan (~16.8k GitHub★) — widely regarded as the strongest open-weight text-to-video model; 1.3B variant runs on 8GB VRAM.Our read
Why it ranks #2
Roughly 16.8k GitHub stars plus strong placement in open-video roundups support Wan as one of the most adopted and capable open-weight families, with a practical small model.Here is the catch
larger checkpoints still need high-end GPUs
generation is slow without optimization
licensing and commercial terms must be checked per checkpoint
Does this well
excellent open-weight quality for its size
small variant lowers hardware barriers
active official releases and broad community support
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-videoMultiple model sizesFirst/last-frame conditioningConsumer-GPU-capable 1.3B variant
Quick facts
More in this area
The rest of the Open source column.- 1Open-Sora (hpcaitech)The category-defining open-source video generator (~29k GitHub★) — text/image-to-video with performance comparable to HunyuanVideo on VBench.
- 3HunyuanVideo (Tencent)Tencent's 13B open video model (~12.4k GitHub★) — a benchmark reference for open-source cinematic text-to-video quality.
- 4CogVideo / CogVideoX (Zhipu)Apache-2.0 CogVideoX (~12.9k GitHub★) — loads natively in HF Diffusers, strong prompt following and smooth frames; a go-to for developers.
- 5LTX-Video (Lightricks)Lightricks' real-time DiT video model (~10.7k GitHub★) — notable for fast, production-capable generation and active releases.
- 6Mochi 1 (Genmo)Genmo's Apache-2.0 Mochi 1 (~3.7k GitHub★) — a recognized open text-to-video model, lower adoption than the leaders above.
- 7HBAI-Ltd/Toonflow-appOpen-source desktop app that turns a novel or script into an animated short drama, chaining AI screenwriting, storyboarding and shot generation.