All models

Seedance 2.0

bytedance/seedance-2.0
ByteDance Video GenerationImage-to-VideoReference ImagesAudio GenerationMultimodal

ByteDance's next-generation video model with a unified multimodal architecture. Generates high-quality video with synchronized audio from text, images, video clips, and audio inputs. Supports multimodal references (up to 9 images, 3 videos, 3 audio files), native audio generation, video editing, video extension, intelligent duration, and adaptive aspect ratio.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "bytedance/seedance-2.0",
    "image": <string>,
    "prompt": <string>
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "bytedance/seedance-2.0", "image": "<string>", "prompt": "<string>"}'

Examples

Parameters

Input
aspect_ratio string required

Video aspect ratio. Ignored if an image is used.

camera_fixed boolean required

Whether to fix camera position

duration integer required

Video duration in seconds

fps number required

Frame rate (frames per second)

generate_audio boolean

Whether to generate audio with the video

image string

Reference image (HTTP(S) URL or base64 data URI) for image-to-video

last_frame_image string

Reference image (HTTP(S) URL or base64 data URI) for last-frame guidance. Only works if an image start frame is also given.

prompt string required

Text prompt describing the video to generate

reference_images array

Reference images (1-4, HTTP(S) URLs or base64 data URIs) to guide video generation for characters, avatars, clothing, or environments. Cannot be used with 1080p resolution or first/last frame images.

reference_video string

Reference video (HTTP(S) URL or base64 data URI) for style/motion guidance

resolution string required

Video resolution

seed integer

Random seed for reproducible generation

watermark boolean required

Whether to add a watermark to the output video

Output
video: URL to the generated video