ByteDance

doubao-seed-1-8-251228

doubao-1-5-pro-32k-250115

doubao-1.5-pro-32k-character-250715

bytedance-seedance-2.0-fast

Native ByteDance passthrough for seedance-2.0-fast

bytedance-seedance-2.0

Native ByteDance passthrough for seedance-2.0

Seedance 2.0 Video Generation

The Seedance 2.0 series of models supports multi-modal input, including images, videos, audio, and text. It is capable of video generation, video editing, and video extension, and can accurately reproduce object details, audio tones, effects, styles, and camera movements while maintaining consistent character traits.It supports text-to-video, image-to-video (first frame/first and last frames), and multimodal reference-based video generation (combinations of images, video, and audio). It offers a Standard Edition (seedance-2.0) and a Fast Edition (seedance-2.0-fast), with the Fast Edition offering lower pricing and faster generation speeds.

Seedream 5.0 lite

Seedream 5.0 Lite is ByteDance’s next-generation multimodal image generation model. It features comprehensive upgrades in cross-modal understanding and logical reasoning, accurately interpreting user intent while maintaining subject consistency; it pioneers online retrieval to synchronize trending topics and new knowledge in real time; and it supports precise instruction adherence, high-definition and efficient generation, and integrated editing.Lightweight, efficient, stable, and reliable, it is optimized for high-frequency creative scenarios such as e-commerce, marketing, and design. It supports an ultra-fast inference API with stable performance, eliminating wait times and offering exceptional value for money.

Seedance 1.5 Pro: Image to Video

The Seedance series offers reliable generation capabilities, making it ideal for production environments. Designed for production-level use, this series prioritizes stability and controllable output. Its image-to-video feature allows a single reference image to drive motion and camera work, making it suitable for dance performances, product demonstrations, and stylistic extensions. The real-time inference API delivers stable performance with no waiting time and is affordably priced.

Seedance 1.5 Pro: Text to Video

The Seedance series offers reliable generation capabilities, making it ideal for production environments. Designed for production-level use, this series prioritizes stability and controllable output. Text-to-video capabilities allow users to generate storyboards and cinematographic styles directly from prompts, enabling rapid prototyping from script to finished video. The real-time inference API delivers stable performance with no waiting time and is affordably priced.

Seedream 4.5

Seedream focuses on Chinese semantic understanding and aesthetic control, making it ideal for generating images for e-commerce and content creation. Seedream 4.5 enhances Chinese prompt understanding and visual quality, balancing both realistic and illustrative styles. It is suitable for general content generation and tool integration, making it easy to incorporate into your production workflow. With its real-time inference API, it offers stable performance, zero wait times, and affordable pricing.