Ads and product concepts
Describe a product in its intended setting, then add a single reveal or interaction. Use text-to-video for early visual ideas before you have a finished product photograph.
Describe a scene from scratch. Set the action, camera, lighting, and sound without uploading an image.
A bicycle courier rides along a coastal road at sunrise. Track the rider from the side, with moving waves and grass in the background.
Use concrete details so you can judge what to keep and what to change in the next attempt.
Describe a product in its intended setting, then add a single reveal or interaction. Use text-to-video for early visual ideas before you have a finished product photograph.
Choose 9:16 and put the subject near the center. Keep important action away from the top and bottom where platform controls or captions may appear.
Give each shot a subject and a purpose: an establishing view, a reaction, or a close-up. Quote spoken lines and specify ambient sound when audio is enabled.
Watch actual model outputs. Each clip identifies its model and source; results vary with the input.
5 seconds · 480p · Audio on · 16:9
A bicycle courier rides along a coastal road at sunrise. Track the rider from the side, with moving waves and grass in the background.
View source and full prompt · Seedancer2 ↗5 seconds · 480p · Audio on · Original image ratio
Keep the perfume bottle still and slowly move the camera closer. Preserve the product shape as studio light moves across the glass.
View the original product image ↗
View source and full prompt · Seedancer2 ↗Start with who or what appears, where the scene happens, and what the subject does. Add a visual style only when it helps define the result.
Choose a fixed shot, tracking movement, or a slow pan. State whether the scene has dialogue, music, or only environmental sound.
Use a short clip for one action. If you select a longer duration, divide the prompt into a beginning, a change, and an ending.
A bicycle courier pauses at a quiet seaside café at sunrise. Medium side shot, slow tracking camera. The courier removes a helmet and looks toward the sea. Warm light, gentle waves and distant birds, no music. 5 seconds, 16:9.
Back to the generator ↑Yes. The text-to-video tool needs a written prompt, not a source image. Seedance creates the subject, scene, and movement from the instructions you provide.
Use this order: subject, action, setting, camera, lighting, and sound. Replace vague praise such as “amazing scene” with visible details such as “low side lighting on a wet street.”
You can write your prompt in either language. Put the intended spoken words in quotation marks and identify who says them. Listen to the generated speech before using it in a finished video.
Set the aspect ratio to 9:16 before generating. Describe vertical framing and leave clear space if you plan to add captions later. Exporting a landscape clip and cropping afterward can cut off the action.
A short duration may not fit every requested action. Remove conflicting camera directions, reduce the number of subjects, and test the most important action before adding secondary details.