Seedance 1.5 Pro turns a written scene or one to two supplied frames into a 4, 8 or 12-second video with optional generated audio. Describe the subject’s actions, camera direction, dialogue and environmental sounds, then choose 480p, 720p or 1080p output and the aspect ratio for your placement. Use Text to Video to develop a scene from words, or Image to Video to anchor the opening composition and optionally define the final frame. The fixed-lens setting helps you request a stationary viewpoint for a portrait, an object action or a small observed transition.
Seedance 1.5 Pro is developed by ByteDance Seed. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Video when your story begins with a written brief. Choose Image to Video when a photograph or illustration already defines the subject, and supply a second image when the final state matters. Both tasks provide duration, resolution, aspect-ratio and generated-audio settings.
Seedance 1.5 Pro Text to Video turns written scenes into videos with synchronized audio and cinematic camera movement. It follows your scene, dialogue and action instructions to build cohesive short clips with expressive characters and coordinated sound.
Seedance 1.5 Pro Image to Video animates images with synchronized audio and first-and-last-frame guidance. It uses the opening image to anchor the subject and composition, while your prompt directs the action and camera movement.
The text task builds the visual scene from your prompt. The image task uses the first URL as the opening frame and an optional second URL as the final frame; the prompt describes the movement between them and the sounds to generate. Review the original task introductions below and open the task that matches your material.
| Model / task | Input and workflow |
|---|---|
| Seedance 1.5 Pro Text to Video | Seedance 1.5 Pro Text to Video turns written scenes into videos with synchronized audio and cinematic camera movement. It follows your scene, dialogue and action instructions to build cohesive short clips with expressive characters and coordinated sound. |
| Seedance 1.5 Pro Image to Video | Seedance 1.5 Pro Image to Video animates images with synchronized audio and first-and-last-frame guidance. It uses the opening image to anchor the subject and composition, while your prompt directs the action and camera movement. |
Write a short sequence with visible actions and audible events, use supplied frames to establish visual states and choose output settings for the finished clip. The examples below show how these instructions can be inspected in actual generation records.
Describe the setting, subject, action and sound together, then enable generated audio. The rainy-bus example starts from a written scene and requests a short continuous shot. Review the resulting movement, dialogue and ambience together when developing a narrative idea.
Supply a portrait image and describe the small actions and exact words to speak. The elevator example asks the woman to hold a button, smile and say a single Mandarin sentence while the camera stays fixed. Inspect facial continuity, mouth movement and the timing of the requested sounds.
Place the opening image first and the ending image second in the image input. The plant example supplies the same potted sprig before and after its leaflets close. These frames give the requested movement a concrete beginning and destination while the prompt explains the transition.
Enable the fixed-lens setting and describe which scene details remain stationary. In the botanical example, the probe advances slightly and the leaflets fold while the pot, bench and framing stay consistent. A stable viewpoint makes local changes easier to review.
Set a duration of 4, 8 or 12 seconds, choose 480p, 720p or 1080p, and select one of six aspect ratios from square to ultrawide and portrait. Plan action beats to fit that duration and review the task estimate with generated audio set as intended.
The first record starts from a maintenance worker holding an elevator button and asks for subtle movement, one Mandarin sentence and an elevator chime. The second supplies two botanical images and asks a probe to touch a leaf as its leaflets close. Read the full prompts, compare the source frames with the videos and play the results to review the requested sound and motion.
Animate this exact photograph for eight seconds as a restrained realistic film portrait. The young maintenance woman shown in the photo is the ONLY visible person for the entire clip. Keep the ENTIRE elevator and the EMPTY yellow hallway on the left exactly like the photograph, perfectly still from first to last frame. Fixed camera, unchanged crop and lighting. Her finger already touches the round button: she gently depresses it and holds it there throughout. Only her facial expression and head move subtly: she looks just to the left of camera toward an unseen neighbor, smiles kindly, then says ONCE with natural clear female Mandarin speech: 别急，我等你。 Keep her unobstructed face, bun, blue overalls and hand anatomy exactly consistent with the reference. A brief distant footstep sound is heard entirely OFF SCREEN before she speaks; the visible hallway stays completely empty. After her sentence, one soft elevator chime. End holding her warm small smile and the same button position. No one walks through the hallway, no duplicate woman, no new faces or bodies, no reflections of people, no door movement, no camera movement, music, subtitles or logos.
Use the supplied images as the first and last frames of one continuous locked four-second botanical macro observation. Preserve the exact pot, sensitive-plant sprig, black bench, task lighting, probe and framing. The probe advances only a few millimeters, briefly touches the main open compound leaf, then withdraws slightly. The paired tiny leaflets progressively fold inward along their existing central midrib, matching the closed main leaf in the final image. Smooth small local motion, no new branches, no morphing plant, no camera movement or cuts. Subtle short mechanical servo sound for the probe and quiet indoor ventilation; no dramatic plant sound, speech, music, titles or logos.
Prepare a written shot or suitable first and last frames, describe the action and audio, and choose a duration that gives each event time to unfold. Use the result as a narrative concept, an animation study or a short scene within an application.
Prepare a clear portrait, write one short spoken line and describe the expression and gestures around it. Generate with audio enabled and inspect the face and speech before using the clip in a character concept or story presentation.
Write a location, visible activity and the sounds associated with it. Use Text to Video to explore rain, transport or indoor atmosphere and review the generated scene as an audiovisual mood study.
Upload the illustration as the first frame and describe a short action that fits the composition. Select an aspect ratio and duration for the intended placement, then review the clip for an animation concept or creative presentation.
Prepare first and last images of the same subject and describe the movement between them. Request a fixed viewpoint to make a plant response, small mechanism or object transition easier to examine in a demonstration.
Choose a supported aspect ratio for the target layout, then write the subject placement and camera direction. Generate a 4, 8 or 12-second clip and use the framing study to plan a social video or presentation sequence.
Retain the prompt, ordered image URLs, audio choice and output settings from a successful online test. Submit the matching task through the API and retrieve its completed video for the creative workflow in your application.
Seedance 1.5 Pro is billed per generated video. The selected duration, resolution and generated-audio option determine the applicable tier; their effect is shown in the task’s estimate. The dynamic table below displays each task’s current lowest available price. Open a task and set the actual 4, 8 or 12-second duration and output options to review the price for that request.
| Model | Provider | Workflow | Max image inputs | Max output resolution | Starting rate |
|---|---|---|---|---|---|
| Seedance 1.5 Pro Text to Video | ByteDance | Text to Video | Not applicable | 1080p | $0.045 / video |
| Seedance 1.5 Pro Image to Video | ByteDance | Image to Video | 2 | 1080p | $0.045 / video |
Test your creative brief online, then bring the verified request into your application.
Enter the prompt and provide the frame images for Image to Video. Choose 4, 8 or 12 seconds, 480p, 720p or 1080p, an aspect ratio, generated audio and the fixed-lens option. Review the estimate, generate the video and inspect its visual events and sound before refining the prompt.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Text to Video for a written scene, or Image to Video for an opening image and an optional ending image. Prepare the prompt’s action, camera and sound instructions, and order the frame images by their role in the shot.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Set duration, resolution and generated audio on the task page to review the corresponding per-video estimate. Plan separate tests for a short scene draft and a longer finished shot.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Seedance 1.5 Pro is a ByteDance Seed video model available on Vidgo through text-based and frame-based tasks. It creates 4, 8 or 12-second clips at 480p, 720p or 1080p, with an option to generate audio and controls for aspect ratio and a fixed lens.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
