Back to tools

Etna

7Volcanoes' AI video generation model capable of creating up to 15-second 4K 60fps clips, targeting short drama and creative content.

Tool categories
Video
Tool links

Tool overview

Etna is a text-to-video model developed by 7Volcanoes, combining Diffusion and Transformer architectures to turn text into video. Its headline features are 4K resolution, 60 frames per second, and up to 15 seconds of duration, which stand out among domestic alternatives. Strategic partnerships with Xiaomi and Kuaishou hint at its commercial applications in short drama exports.

Free daily credits lower the barrier, but due to computing costs, the free tier produces only 720P video; higher resolutions require a paid membership whose details are not yet public. Comparisons with models like OpenAI Sora reveal gaps in motion coherence and semantic fidelity—complex scenes may show unnatural distortions or logic errors.

Etna suits short-drama teams, ad creatives, and AI video enthusiasts who need quick, high-resolution clips and can tolerate short length and some quality issues. However, it is not yet reliable enough for professional filmmakers pursuing cinematic stability, long-form storytelling, or precise semantic control, and should be adopted with caution.

Related social content