Models/Collections/Seedance · Seedream

Seedance · Seedream

From ByteDance's Seed team — TikTok's parent applying its short-video expertise to generation. Seedream covers image generation and editing; Seedance delivers motion-aware video with fast iteration tiers.

Models

Realistic image generation and consistent multi-turn editing, with native transparency and layer decomposition

$0.02/ imageUp to 1.5K (2.61 MP)
Run

Fast, cost-efficient image generation and multi-reference editing with layer decomposition

$0.01926/ image
Run

Professional multimodal video generation with native 30-second clips, large-scale reference control, and precise localized editing

$0.1025/ secondText/Image to Video · 480p
Run

Flagship image model for controlled editing, multi-reference generation, and layer-aware visual workflows

$0.04815/ image1.5K
Run

Unified multimodal audio-video generation with multi-reference input and physics-aware motion

$0.07/ second480p
Run

Compact Seedance 2.0 variant for faster, lighter multimodal video generation workflows

$0.036/ second480p · text/image to video
Run

Faster multimodal video generation tuned for latency and iteration speed

$0.06/ second480p
Run

Responsive text-to-image generation with real-time search and precise prompt adherence

$0.035/ image
Run

Seedream 4.5 high fidelity multi reference text to image model

$0.04/ image
Run

Fast Seedance 1.0 Pro video generation for dance content

$0.00629/ second16:9 · 480p
Run

High speed 4K AI image generation and editing model

$0.03/ image
Run

Seedance 1.0 Pro high fidelity 1080p text and image to video

$0.01925/ second480p
Run

Model guides

Seedream 5.5

Prompting

How to write text-to-image prompts for Seedream 5.5: choosing between resolution tiers and exact sizes, layering a prompt into directives, and setting exact copy on the image.

Read the guide →Seedream 5.5

Editing images

How to edit images with Seedream 5.5: an instruction to recolor, clean up or relight one photo, a drawn mark to pick the target, and edits chained over several rounds.

Read the guide →Seedream 5.5

Multi-reference composition

How to compose one image from up to ten references with Seedream 5.5: assigning roles, dressing one model in a garment range, arranging a product set and sizing the output.

Read the guide →Seedream 5.5

Layer decomposition

How to split one image into a base image and transparent layers with Seedream 5.5, from layer positions and split size to reading the text on text layers.

Read the guide →Seedream 5.5

Transparent backgrounds

How to make cut-out assets with Seedream 5.5: transparent output from a prompt or an existing photo, the auto default, matching sticker sets and soft hair edges.

Read the guide →Seedance 2.5

Prompting

How to prompt Seedance 2.5 for directed text-to-video: the five-layer shot scaffold, camera vocabulary the model reads directly, second-level timing, and native audio.

Read the guide →Seedance 2.5

Image to video and keyframes

How to turn a still into video with Seedance 2.5: animate a first frame, interpolate a first and last frame, loop a still, and sequence images as keyframes.

Read the guide →Seedance 2.5

Multimodal reference

How to compose up to 30 images, 10 videos, and 10 audio clips into one Seedance 2.5 call with typed @-tag addressing, from cast ensembles and product families to audio-driven scenes.

Read the guide →Seedance 2.5

Editing video

How to edit an existing clip in place with Seedance 2.5 using inputs.video: remove and replace elements, restyle and relight the frame, swap backgrounds, and edit by timestamp.

Read the guide →Seedance 2.5

Long-form and extension

How to structure a 30-second Seedance 2.5 brief as one continuous take or a multi-shot passage, hold continuity across the runtime, and extend past 30 seconds with inputs.video.

Read the guide →Seedance 2.5

Motion and performance transfer

How to drive Seedance 2.5 with a reference video for motion, camera, and lip-sync while a reference image supplies identity: motion transfer, character swaps, and clay to finished shot.

Read the guide →Seedance 2.5

Multilingual video

How to generate video in 10+ languages with Seedance 2.5: native lip-sync from a text prompt, switching languages within one clip, and controlling accent and delivery.

Read the guide →Seedream 5.0 Pro

Prompting

How to prompt Seedream 5.0 Pro for text-to-image, reference-guided editing, and multi-image fusion in commercial workflows: campaign posters, product variants, and editorial still-life.

Read the guide →Seedream 5.0 Pro

Multilingual text rendering

How to prompt Seedream 5.0 Pro for accurate in-image text across 15 native languages, from French posters with accented characters to Arabic, Thai, Korean, and Japanese scripts.

Read the guide →Seedream 4.5

Prompting for layered, high-resolution scenes

How to write prompts for Seedream 4.5, from short interpretive prompts to layered scene descriptions, with legible text rendering at 2K to 4K.

Read the guide →