Kuaishou's general-purpose video generation model.
Model Category
Text-to-Video Models — 85+ AI Video Generators From a Prompt
Kling v3, Sora 2, Veo 3, Wan 2.6, Seedance 2.0 and more — 85+ text-to-video models generate a clip straight from a written prompt, no starting image required.
85+ Text-to-Video Models15s Max Clip Duration (Grok Imagine T2V)
Text-to-video turns a written prompt straight into a clip, no starting image required. It's the second-largest text-to-video category in the catalog at 85+ models, running everything from fast turbo generations to flagship names like Sora 2, Veo 3 and Kling v3.
Text-to-Video Models
85+ Text-to-Video Models, One Open Generative AI Catalog
Every text-to-video model below runs through the same Video Studio prompt box — no separate accounts, no separate pricing, no filters swapped in per model.
OpenAI's video generation model.
Google's video generation model.
Alibaba's Wan family, hosted here at version 2.6.
ByteDance — 4 aspect ratios, 5/10/15s duration, basic/high quality.
MiniMax's Hailuo 02/2.3 line — full HD, fast variant included.
Runway's video generation model.
xAI — up to 15s duration, fun/normal/spicy modes, 5 aspect ratios.
Hosted vs. run it locally
Render in the Cloud, or on Your Own GPU
Open Generative AI ships the same text-to-video catalog two ways — a hosted app with zero setup, and a self-run Wan2GP server that generates video entirely on your own machine.
Hosted
The hosted app runs all 85+ text-to-video models — Kling v3, Sora 2, Veo 3, Wan 2.6, Seedance 2.0, Hailuo 2.3, Runway Gen-3 and more — with no GPU required.
Run It Locally
Local text-to-video generation runs through Wan2GP on a self-run CUDA or ROCm GPU server: Wan 2.2, Hunyuan Video and LTX Video (the fastest local option) are the documented video models.
Compare
Three Text-to-Video Models, Side by Side
A quick look at three representative models in the catalog — pick the one that matches the clip you're after.
| Model | Provider / Source | What it's built for |
|---|---|---|
| Kling v3 | Kuaishou | General-purpose text-to-video generation |
| Sora 2 | OpenAI | Text-to-video generation |
| Seedance 2.0 | ByteDance | 16:9/9:16/4:3/3:4 ratios, 5/10/15s duration, basic/high quality |
Swipe to see the full table
FAQ
Text-to-Video Model FAQ
85+, including Kling v3, Sora 2, Veo 3, Wan 2.6, Seedance 2.0, Hailuo 2.3, Runway Gen-3 and Grok Imagine T2V.
Explore more
More Open Generative AI Model Categories
This category pairs closely with the ones below, plus the Video Studio page that runs it end to end.
Generate a Video With Open Generative AI — Free, Right Now
85+ text-to-video models, no content filters, no subscription. No account required to try it.
Try Free