Bytedancevideo

Complete Guide to Using Seedance 1.5 Pro

ByteDance's cinematic video generation model with camera control, multi-resolution output, and optional audio.

Overview

Seedance 1.5 Pro is ByteDance's flagship video generation model, capable of producing high-quality video from text descriptions alone or conditioned on up to two reference images. It delivers smooth, cinematic motion with strong prompt adherence and supports resolutions from 480p to 1080p.

A key differentiator is the fixed lens option, which locks the camera position for stable, professional shots. This is particularly valuable for product showcases, interviews, and any scene where camera movement would be distracting. The model also supports optional audio generation, adding synchronized sound effects to the video output.

With flexible duration options of 4, 8, or 12 seconds and a wide selection of aspect ratios including ultrawide 21:9, Seedance 1.5 Pro adapts to diverse creative needs from social media shorts to cinematic previews. At 98 credits, it offers strong value compared to premium video models.

Capabilities

Text-to-video and image-conditioned video generation
Fixed lens mode for stable, tripod-style camera shots
Optional synchronized audio generation
Resolution options from 480p to 1080p
Flexible duration from 4 to 12 seconds
Support for up to 2 reference images for visual conditioning

Use Cases

Product demo videos with stable camera framing

Social media video content across multiple aspect ratios

Cinematic scene previews and mood boards

Image-to-video animation of still photographs

Short narrative clips with synchronized audio

Input Parameters

prompt

textarearequired

Enter video description (3-2500 characters).

Write a clear description of the scene, action, and mood. Include camera direction cues like 'slow pan', 'close-up', or 'wide establishing shot'. Must be 3-2500 characters.

input_urls

file

Upload up to 2 reference images (JPEG/PNG/WebP, ≤10MB each).

Upload 0 to 2 reference images. With no images, the model generates purely from text. One image provides a starting frame. Two images define start and end frames for interpolation.

aspect_ratio

selectrequired

Select the frame dimensions.

Choose the frame dimensions. 16:9 for standard widescreen, 9:16 for vertical/mobile, 21:9 for cinematic ultrawide, 1:1 for square social posts.

Options

1:121:94:33:416:99:16

Default: 16:9

resolution

select

Standard (480p) / High (720p).

480p is fastest and cheapest for previews. 720p is the default balance of quality and speed. 1080p delivers full HD output for final production.

Options

480p720p1080p

Default: 720p

duration

selectrequired

4s / 8s / 12s

4 seconds for quick loops and transitions. 8 seconds for standard scenes. 12 seconds for extended narrative sequences.

Options

4s8s12s

Default: 8

Lock Camera Position

toggle

Enable to keep the camera view static and stable.

Enable this for a locked camera position. Ideal for product showcases, talking-head content, and any scene requiring visual stability.

Default: false

generate_audio

toggle

Enable to create sound effects for the video (additional cost applies).

Enable to generate synchronized sound effects. Note that audio generation adds processing time and cost. Best used for scenes where ambient sound enhances the result.

Default: false

NSFW Filter

toggle

Enable NSFW content filtering.

Default: false