Create cinematic video and high-fidelity images with ByteDance models through one LinkModel API.
ByteDance Seed builds next-generation visual models: Seedance creates controllable audio-video stories up to 30 seconds long, while Seedream generates high-fidelity images with advanced reasoning and precise editing.
Choose Seedance for video generation and Seedream for image creation and editing. The catalog below reflects the models currently listed on LinkModel, with supported tasks, request details, and available pricing.
6 models listed
Generate synchronized audio-video from text, images, video, and audio references. Compare Seedance models for 30-second narrative generation, shorter multimodal workflows, and model-specific editing controls.
Seedance2.5ByteDance’s production-oriented multimodal video model for generating and editing coherent clips up to 30 seconds, with synchronized audio, timestamp-level control, and up to 30 image, 10 video, and 10 audio references for stronger character, scene, motion, and style consistency.
Seedance2.0Seedance 2.0 is a multimodal controllable video generation model developed by ByteDance’s Seed Team. Launched in early February 2026, it is now integrated into Doubao, Jimeng AI, and Volcano Engine (Model ID: doubao-seedance-2-0-260128), with an accelerated version—Seedance 2.0 Fast—available for low-latency scenarios.
Create text-rich campaign visuals, product imagery, reference-led compositions, and precise image edits with ByteDance's Seedream family.
Seedream5.0 LiteByteDance's intelligent image model with Chain of Thought visual reasoning and real-time web search, comprehensively upgraded in understanding, reasoning, and generation, supporting up to 4K output and 14-image reference editing.
Seedream4.0ByteDance's multimodal image creation engine unifying text-to-image generation and editing in one architecture, supporting up to 4K output, 30+ art style switching, and multi-reference batch generation with 10x faster inference.
Seedream4.5ByteDance's unified image generation and editing model with precise text rendering, native 4K resolution, and multi-image reference editing, supporting professional typography, material fidelity, and brand visual consistency for commercial design.
Seedream5.0 ProA professional image generation and editing model from ByteDance, built for strong prompt following, text rendering, multi-image reference, and high-fidelity visual detail across commercial design and creative production.
Among the ByteDance models currently available on LinkModel, choose Seedance for video and Seedream for images. Use Seedance 2.5 for 30-second, reference-heavy audio-video creation and precise editing; Seedance 2.0 for workflows up to 15 seconds. Use Seedream 5.0 Pro for text-rich professional visuals, or Seedream 5.0 Lite for reasoning-led image generation.
Multi-shot storytelling with large reference sets, native audio, and targeted edits within a generated video.
Up to 30 seconds · native audio · multi-reference inputs · timestamp-level editing
Official source ↗Short audio-video clips combining text instructions with image, video, or audio references.
Up to 15 seconds · synchronized stereo audio · multimodal references
Official source ↗Information-dense layouts, multilingual typography, commercial design concepts, and precise regional edits.
Professional text rendering · spatial grounding · pixel-level editing
Official source ↗Image generation that requires visual reasoning across complex subject relationships, reference assets, or external knowledge.
Visual reasoning · multimodal generation · web-search-assisted creation
Official source ↗Move from individual generations to complete visual workflows across video, image, and image-to-video production.
Turn campaign concepts, product references, and storyboards into short-form video with Seedance. Use text, images, video, or audio references to control characters, composition, motion, and sound across a generated sequence.
Use Seedream to create product concepts, localized campaign assets, text-rich promotional graphics, and controlled image variations. Keep approved references in the workflow when generating new formats or regional versions.
Build multi-shot concepts and audio-video stories with Seedance 2.5. Generate sequences up to 30 seconds, work with larger reference sets, and apply targeted edits without recreating the entire concept.
Create the visual direction with Seedream, approve the characters and composition, then animate the result with a supported Seedance image-to-video model. This connects image development and video production in one LinkModel account.
Keep model access, credentials, and usage management together while choosing the ByteDance model that fits each production task.
Use the same LinkModel API key across supported ByteDance video and image models.
Track usage and pay-as-you-go charges without maintaining a separate ByteDance or Volcano Engine account.
Explore new models while keeping your LinkModel account, credentials, billing, and task history in one place.
Use one LinkModel credential to move from model selection to a completed video or image generation.
Create a LinkModel API key and use it to authenticate requests across supported Seedance and Seedream models.
Open the model page to confirm its identifier, supported task, and required input parameters before sending a request.
Send the generation request, track its task status, and retrieve the generated video or image when processing completes.
FAQ
Model capabilities and selection guidance are reviewed against the official ByteDance sources listed here.
Editorial content reviewed: August 28, 2026
ByteDance and its model names belong to their respective owners. LinkModel is an independent API aggregation platform and does not imply a formal relationship.
