Seedance 2.0

Description

ByteDance flagship — native audio, advanced physics, reference-to-video.

Seedance. Video generation from ByteDance

Capabilities

Vendor

ByteDance

Family

Seedance

Type

Video

Model ID

Tasks

fal.ai: Text to video, Image to video, Reference to video · Higgsfield: Text to video, Image to video, Reference to video · KREA: Text to video, Image to video, Reference to video · Venice: Text to video, Image to video, Reference to video

Seed

fal.ai: Can be set. · KREA: Can be set.

Inputs

Prompt

Optional

Image

Optional

Video

Optional

Audio

Optional

End frame

Supported

Max images

9

Reference images

Up to 9 reference images.

Reference videos

Up to 3 reference videos.

Reference audio

Up to 3 reference audio clips.

Reference total

Up to 12 references in total.

Source video

Accepted.

Source audio

Accepted.

Outputs

Duration

fal.ai: 4–15 seconds · Higgsfield: 4–15 seconds · KREA: 4–15 seconds · Venice: 4–15 seconds

Resolution

fal.ai: 480p, 720p, 1080p, 4k · Higgsfield: 480p, 720p, 1080p · KREA: 480p, 720p, 1080p, 4k · Venice: 480p, 720p, 1080p, 4k

Aspect ratios

fal.ai: auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 · Higgsfield: auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 · KREA: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 · Venice: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Audio

fal.ai: Generated, and the catalog records a switch. · Higgsfield: Generated, and the catalog records a switch. · KREA: Generated, and the catalog records a switch. · Venice: Generated, and the catalog records a switch.