google/gemini-omni-flash

Creates video with synchronized audio from text input. Grounded in Gemini's real-world knowledge, with improved physics understanding for more coherent motion and interaction.

Learn more about Gemini Omni Flash

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

Open in Sandbox

Input

Prompt*

A high-fashion model stands in a stark concrete gallery space, wearing a sculptural avant-garde garment — exaggerated architectural shoulders, asymmetric draping in matte black and oxblood, structured folds that catch the light like origami. Her makeup is editorial and graphic: bleached brows, a single bold slash of pigment across the eyes, porcelain skin. She moves in slow, deliberate poses — a sharp turn of the head, one arm extending into a severe angular line, fabric shifting with each motion. The camera circles her in a slow orbital dolly, then cuts to a locked-off low-angle hero shot. Hard directional lighting from one side carves deep shadows and sharp highlights, with a single rim light separating her silhouette from the void-black background. High-contrast, desaturated palette with one accent of deep red. Editorial, sculptural, intense, slightly otherworldly. Shot on medium format, crisp detail, fashion-film aesthetic

Aspect Ratio

Duration

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0aa06549/SqtFBfF9UAqFt1vfdpHIN_a7c736c69b4f4c0486dbef648a7fa496.mp4",
    "content_type": "video/mp4",
    "file_name": "a7c736c69b4f4c0486dbef648a7fa496.mp4",
    "file_size": 1968680
  }
}

Billing is based on total token consumption. Tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.125 per second of video.