Skip to main content
Generate videos from text prompts, source frames, or multimodal references. Choose a featured model below, then use the workflow endpoint that matches your inputs.

​
Top models

ByteDanceVideoSeedance 2.0Generate videos from text, first and last frames, or image, video, and audio references.View API reference →ByteDanceVideoSeedance 2.5Create videos from text, images, or multimodal references, then edit or extend existing footage.View API reference →KlingVideoKling 3.0Cinematic text-to-video and image-to-video with fluid motion, native audio, and multiple quality tiers.View API reference →AlibabaVideoWan 3.0Generate up to 30 seconds from text, first and last frames, or multimodal image, video, audio, document, and web references.View API reference →
Explore every available video model in the Higgsfield video generator.

​
Quick start

1

Choose a model

Open a featured model page and select the endpoint that matches your inputs.
2

Submit the request

Authenticate with Authorization: Key <key-id>:<secret> and send the endpoint-specific JSON body.
3

Retrieve the video

Poll the request status or configure webhooks for production workloads.