Nano Banana 2.1 现已上线 — Google 最新模型 | 立即体验 →
Seedream Models

Seedream Models

Seedream integrates image generation and image editing capabilities into a single, unified architecture.

Seedream integrates image generation and image editing capabilities into a single, unified architecture.

所有模型

18 个模型
bytedance/seedream-v5.0-pro/edit10% OFF
image-to-image$0.0450$0.0405

bytedance/seedream-v5.0-pro/edit

Seedream V5.0 Pro Edit by ByteDance edits and generates images from single-image or multi-reference inputs, supporting up to 10 reference images, aspect ratio selection, and 1K / 2K output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-pro10% OFF
text-to-image$0.0450$0.0405

bytedance/seedream-v5.0-pro

Seedream V5.0 Pro Text to Image by ByteDance generates high-quality images from text prompts, with aspect ratio selection, strong prompt following, and 1K / 2K output tiers for flexible image creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-flash/edit10% OFF
image-to-image$0.0270$0.0243

bytedance/seedream-v5.0-flash/edit

Seedream V5.0 Flash Edit by ByteDance edits and generates images from single-image or multi-reference inputs faster and at lower cost than Seedream V5.0 Pro Edit, supporting up to 10 reference images, aspect ratio selection, and 1K / 1.5K / 2K output at one price. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-flash10% OFF
text-to-image$0.0270$0.0243

bytedance/seedream-v5.0-flash

Seedream V5.0 Flash Text to Image by ByteDance generates images from text prompts faster and at lower cost than Seedream V5.0 Pro, with aspect ratio selection, multilingual text rendering, and 1K / 1.5K / 2K output at one price. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-pro/layer-decomposition
image-to-image$0.7500

bytedance/seedream-v5.0-pro/layer-decomposition

Seedream V5.0 Pro Layer Decomposition separates a single image into a base image and transparent layers, enabling flexible compositing, image editing, asset extraction, and layered design workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-flash/layer-decomposition
image-to-image$0.4590

bytedance/seedream-v5.0-flash/layer-decomposition

Seedream V5.0 Flash Layer Decomposition separates a single image into a base image and transparent layers faster and at lower cost than Seedream V5.0 Pro, enabling flexible compositing, image editing, asset extraction, and layered design workflows at one price for 1K / 1.5K / 2K. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v4.5/edit
image-to-image$0.0400

bytedance/seedream-v4.5/edit

Seedream 4.5 Edit preserves facial features, lighting, and color tone from reference images, delivering professional, high-fidelity edits up to 4K with strong prompt adherence. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

bytedance/seedream-v4.5/edit-sequential
image-to-image$0.0400

bytedance/seedream-v4.5/edit-sequential

Seedream 4.5 Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

bytedance/seedream-v5.0-lite/edit
image-to-image$0.0350

bytedance/seedream-v5.0-lite/edit

Seedream 5.0 Lite Edit by is a state-of-the-art image editing model preserving facial features, lighting, and color tones from reference images. Features high-fidelity editing with professional quality, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-lite/edit-sequential
image-to-image$0.0350

bytedance/seedream-v5.0-lite/edit-sequential

Seedream 5.0 Lite Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v4.5
text-to-image$0.0400

bytedance/seedream-v4.5

Seedream 4.5 is a next-gen text-to-image model optimized for typography—crisper text rendering, stronger prompt adherence, and up to 4K output for posters and brand visuals. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

bytedance/seedream-v4/edit
image-to-image$0.0270

bytedance/seedream-v4/edit

Seedream V4 Edit is state-of-the-art image editing model that outperforms Nano Banana in fidelity and edit quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v4
text-to-image$0.0270

bytedance/seedream-v4

Seedream 4.0 by is a state-of-the-art image generation model delivering high-fidelity outputs and outperforming Nano Banana. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-lite
text-to-image$0.0350

bytedance/seedream-v5.0-lite

Seedream 5.0 Lite by is a state-of-the-art text-to-image model with enhanced typography, clear text rendering for posters and brand visuals, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v4.5/sequential
text-to-image$0.0400

bytedance/seedream-v4.5/sequential

Seedream 4.5 Sequential generates multi-image sets with consistent characters and objects, unifying palette, lighting, and style across all outputs. Supports up to 4K results for campaigns, storyboards, and product lines. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

bytedance/seedream-v4/edit-sequential
image-to-image$0.0270

bytedance/seedream-v4/edit-sequential

Seedream 4.0: 4K image generation and editing with character and object consistency and sequential multi-image outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v5.0-lite/sequential
text-to-image$0.0350

bytedance/seedream-v5.0-lite/sequential

Seedream 5.0 Lite Sequential generates multi-image sets with consistent characters and objects, unifying palette, lighting, and style across all outputs. Supports up to 4K results for campaigns, storyboards, and product lines. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bytedance/seedream-v4/sequential
text-to-image$0.0270

bytedance/seedream-v4/sequential

Seedream 4.0 by creates 4K images with editing, character/object consistency and sequential multi-image generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Seedream Models

Seedream is ByteDance's advanced AI image generation and editing model suite, built for high-quality visual creation, professional image editing, sequential generation, and commercial creative workflows. The collection includes Seedream 5.0 Pro, Seedream 5.0 Lite, Seedream 4.5, Seedream 4, Seedream 3, and Seededit models, covering text-to-image generation, image editing, image-to-image transformation, sequential image creation, and multi-step visual refinement.

Seedream 5.0 Pro is the flagship model in the Seedream family, delivering stronger prompt adherence, sharper detail rendering, more stable compositions, and higher-quality visual output for demanding creative and production workflows. It is designed for brand key visuals, advertising creatives, e-commerce product images, posters, concept art, character visuals, fashion imagery, and premium marketing assets.

Fast Mode is now available for Seedream workflows, giving creators and developers a faster option for rapid iteration, preview generation, and high-volume creative production. Users can choose between premium quality and faster turnaround depending on their workflow needs.

Core Model Capabilities

Seedream 5.0 Pro Image Generation:

Create high-quality images from natural-language prompts with stronger visual detail, cleaner composition, improved realism, and production-ready output quality.

Seedream 5.0 Pro Image Editing:

Edit and transform existing images with precise natural-language instructions while preserving subject identity, lighting, structure, and visual consistency.

Seedream 5.0 Flash Image Generation:

Generate high-quality images with faster turnaround for rapid ideation, prompt exploration, preview creation, and high-throughput visual workflows.

Fast Mode:

Use prompt-fast-optimized generation and editing workflows for faster previews, prompt testing, creative iteration, and scalable image production.

Text-to-Image Generation:

Generate photorealistic, illustrated, cinematic, or design-focused images from prompts for marketing, product visuals, posters, social media assets, and concept development.

Image Editing and Refinement:

Modify images through prompt-guided edits, including style adjustment, subject refinement, background changes, object-level edits, and creative retouching.

Sequential Image Workflows:

Create or edit images across sequential steps, helping maintain visual direction, character consistency, and creative continuity during multi-step production.

Standard, Lite, and Pro Options:

Use Seedream Lite for faster, more efficient generation; earlier Seedream versions for stable image workflows; and Seedream 5.0 Pro for premium-quality creative output.

Commercial Creative Workflows:

Support advertising, e-commerce, fashion, brand design, entertainment concept art, social media campaigns, poster design, and professional visual production.

Seedream Models on WaveSpeedAI give creators and developers fast access to ByteDance's image generation and editing models with scalable APIs, flexible pricing, Fast Mode support, and production-ready visual quality.

Seedream Models API — 价格与性能

通过单一 REST API 运行 Seedream Models 系列中的任意模型。按生成计费 — 无订阅、无最低消费 — 在 99.9% 可用性的基础设施上提供行业领先的延迟。

为什么在 WaveSpeedAI 上运行 Seedream Models

透明定价

每个 Seedream Models 模型都有按调用计价。价格在每个模型的页面上列出 — 不收取额外的平台费。

为低延迟优化

大多数 Seedream Models 图像模型在 2 秒内完成。视频和 3D 模型比自托管方案快数倍。

99.9% 可用性

多区域故障转移和自动重试可确保您的生产流量保持在线 — 即使在供应商故障期间。

常见问题

Seedream Models API 多少钱?+

每个模型在其模型页面上都列有自己的按调用价格。我们按每次成功生成计费,没有订阅费或最低消费。

Seedream Models 模型在 WaveSpeedAI 上有多快?+

本系列中的图像模型通常在 2 秒内完成。视频和 3D 模型取决于时长和分辨率,但通常比自托管运行快数倍。

不用信用卡可以试用 API 吗?+

符合条件的新账户可能获得 $1 的推广额度,用于无需信用卡试用 Seedream Models 模型。并非每次注册都会获得试用额度,请在生成前查看账户余额。

有速率限制吗?+

标准账户有充足的并发任务限制。企业版计划提供自定义 RPM、更高并发和专用容量 — 详情请联系销售。