AI Models

Open full-modal video model with native 2K output and dual-channel audio.

Alibaba Wan 3.0 video model with native audio and reference consistency.

Short-form cinematic video with native audio and lip-sync.

Discover sharper detail, faithful references, precise edits, and the Flare and Sunburst API profiles.

Create images from text or edit up to ten references with Qwen Image 2.1.

Google Gemini image model for 1K to 4K generation, reference consistency, and readable text.

Cinematic motion, stereo audio, and Omni Reference control.

xAI image-to-video model for turning a still into motion.

Google DeepMind's any-to-any multimodal video model on FastMoro AI.

The original Happy Horse video model on FastMoro AI.

OpenAI's GPT Image 2 for text-to-image and image editing.

Seedance 2.0 text-to-video workflow with native audio options.

Animate a still with Seedance 2.0 image-to-video.

Keep identity and style with Seedance 2.0 reference-to-video.