New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
AI video generation models
Compare AI video generation models — Sora, Veo, Kling, Runway and other text-to-video systems — by capability, resolution, length and availability.
No models found
About AI video generation models
AI video generators create short clips from text or image prompts, and the field is moving fast. Models such as Sora, Veo, Kling and Runway differ in clip length, resolution, motion coherence and prompt control. When evaluating a text-to-video model, consider how well it maintains temporal consistency across frames, the maximum clip length, supported resolutions and whether it offers image-to-video conditioning. Availability varies widely — some models are open to everyone, others are gated or invite-only. Browse the list below to compare video generation models by provider and availability, check the benchmarks page for capability comparisons, and use compare to evaluate two systems side by side before committing to a workflow.
Frequently asked questions
How do I choose the right model?
Weigh raw capability against practical constraints like context window, latency, licensing and price. Use the benchmarks page to compare rankings and the compare tool to evaluate two candidates side by side.
Where can I see benchmark scores?
Visit the benchmarks page to compare these models on standardised tests, then use the compare tool for a detailed side-by-side of any two models.