All Models

WaveSpeed logo

Hunyuan Video 1.5

Hunyuan Video 1.5 generates video from text or animates reference images, combining coherent motion with continuity in subject identity and visual style.

Image to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 5s ยท Resolution: 480p$0.10 / run
Duration: 5s ยท Resolution: 720p$0.20 / run
Duration: 8s ยท Resolution: 480p$0.16 / run
Duration: 8s ยท Resolution: 720p$0.32 / run

Text to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 5s ยท Size: 832 ร— 480$0.10 / run
Duration: 5s ยท Size: 480 ร— 832$0.10 / run
Duration: 5s ยท Size: 1280 ร— 720$0.20 / run
Duration: 5s ยท Size: 720 ร— 1280$0.20 / run
Duration: 8s ยท Size: 832 ร— 480$0.16 / run
Duration: 8s ยท Size: 480 ร— 832$0.16 / run
Duration: 8s ยท Size: 1280 ร— 720$0.32 / run
Duration: 8s ยท Size: 720 ร— 1280$0.32 / run

Hunyuan Video 1.5

Hunyuan Video 1.5 supports two starting points for video creation: a written scene description or an existing image. Text-led generation builds a moving scene from the described content. Image-led generation uses supplied artwork as its visual foundation, with text guiding the action and camera movement.

The model emphasizes coherent movement and consistent subject identity. When animating an image, it also retains the reference's visual style, making it useful for developing motion around an established character or illustration.

What it's good for

These complementary approaches suit visual development across a production. A filmmaker can explore a scene from a script idea, then use character artwork to develop an image-based shot with a more defined appearance.

For promotional work, image animation can turn campaign artwork into moving material. Text-to-video generation also supports early studies of settings and action, giving teams footage to discuss alongside storyboards before a shoot or animation project.

Model ID

wavespeed-ai/hunyuan-video-1.5

Output Type

Video

Pricing

From $0.10 / run

Provider

WaveSpeed

Hosting

Passthru

Hunyuan Video 1.5

Hunyuan Video 1.5 supports two starting points for video creation: a written scene description or an existing image. Text-led generation builds a moving scene from the described content. Image-led generation uses supplied artwork as its visual foundation, with text guiding the action and camera movement.

The model emphasizes coherent movement and consistent subject identity. When animating an image, it also retains the reference's visual style, making it useful for developing motion around an established character or illustration.

What it's good for

These complementary approaches suit visual development across a production. A filmmaker can explore a scene from a script idea, then use character artwork to develop an image-based shot with a more defined appearance.

For promotional work, image animation can turn campaign artwork into moving material. Text-to-video generation also supports early studies of settings and action, giving teams footage to discuss alongside storyboards before a shoot or animation project.