Skip to content

ByteDance · Image

Doubao Seedream 4-0

ByteDanceImageSeedream familyOne of its sources says the weights aren't publicly available.

Newer version: Seedream 5.5. We compared release dates and version names in our catalogue.

From Empiriolabs's listing:
Unified image generation and editing with up to 14 reference images, batch sets of up to 15, and 1K to 4K output at one flat per-image price.
llminfo IQ
93.4
Market median price
$0.03 /image
Max context
4K
Listings
22

Evidence and sources

llminfo IQ 93.4, ranked among image generation models. From 182 benchmarks. A fair amount of data behind it.How llminfo IQ is computedReleased 9 Sep 2025
Sources: LMArena data, CometAPI Pricing data, EmpirioLabs data, Models.dev data, llminfo researchPrimary data from LMArena from CometAPI Pricing: name from EmpirioLabs: primary mode, description from Models.dev: weights availability from llminfo research: release date

Input & output

as stated by the model's providers
Text
Images
Text
Images

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction calling

Listings

 Cometapidoubao-seedream-4-0-250828 · 250828Sources: CometAPI data, CometAPI Pricing dataNot published by the provider—$0.04
 Llmgatewayseedream-4-0Source: LLMGateway data2K—$0.035
 MeganovaBytedance/seedream-4-0-250828 · 250828Source: MegaNova dataNot published by the provider$0.03—
 NanoGPTseedream-v4Source: NanoGPTNot published by the provider$0.03—
 Replicatebytedance/seedream-4Sources: LiteLLM data, Replicate data docsNot published by the provider$0.03—
 Empiriolabsseedream-4-0Source: EmpirioLabs dataNot published by the provider$0.06—
 fal.aifal-ai/bytedance/seedream/v4/edit · editSources: Fal.ai data, LiteLLM dataNot published by the provider$0.03—
 fal.aifal-ai/bytedance/seedream/v4/text-to-image · text-to-imageSources: Fal.ai data, LiteLLM dataNot published by the provider$0.03—
 Together AIByteDance-Seed/Seedream-4.0Sources: LiteLLM data, Together AI dataNot published by the provider$0.03—
 Veniceseedream-v4Source: Venice.ai dataNot published by the provider$0.05—
 Veniceseedream-v4-edit · editSource: Venice.ai dataNot published by the provider$0.05—

11 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Image generation

GenExam22 related benchmarks · 22 results
RISEBenchSource: RISEBench data
UniGenBench++136 related benchmarks · 136 results
Source: UniGenBench++ data
BenchmarkScore
(Chinese) - 2D
(Chinese Long) - 2D
(Chinese Long) - 3D
(Chinese Long) - Action-Overall
Show 132 more benchmarksHide 132 benchmarks
BenchmarkScore
(Chinese Long) - Animal
(Chinese Long) - Attribute-Overall
(Chinese Long) - Color
(Chinese Long) - Comparison
(Chinese Long) - Composition
(Chinese Long) - Compound-Overall
(Chinese Long) - Consistency
(Chinese Long) - Contact
(Chinese Long) - Expression
(Chinese Long) - Feature matching
(Chinese Long) - Full body
(Chinese Long) - Grammar-Overall
(Chinese Long) - Hand
(Chinese Long) - Imagination
(Chinese Long) - Inclusion
(Chinese Long) - Layout-Overall
(Chinese Long) - Logical Reasoning
(Chinese Long) - Material
(Chinese Long) - Negation
(Chinese Long) - Non Contact
(Chinese Long) - Overall
(Chinese Long) - Pronoun Reference
(Chinese Long) - Quantity
(Chinese Long) - Relationship-Overall
(Chinese Long) - Shape
(Chinese Long) - Similarity
(Chinese Long) - Size
(Chinese Long) - State
(Chinese Long) - Style
(Chinese Long) - Text
(Chinese Long) - World Knowledge
(Chinese) - 3D
(Chinese) - Action-Overall
(Chinese) - Animal
(Chinese) - Attribute-Overall
(Chinese) - Color
(Chinese) - Comparison
(Chinese) - Composition
(Chinese) - Compound-Overall
(Chinese) - Consistency
(Chinese) - Contact
(Chinese) - Expression
(Chinese) - Feature matching
(Chinese) - Full body
(Chinese) - Grammar-Overall
(Chinese) - Hand
(Chinese) - Imagination
(Chinese) - Inclusion
(Chinese) - Layout-Overall
(Chinese) - Logical Reasoning
(Chinese) - Material
(Chinese) - Negation
(Chinese) - Non Contact
(Chinese) - Overall
(Chinese) - Pronoun Reference
(Chinese) - Quantity
(Chinese) - Relationship-Overall
(Chinese) - Shape
(Chinese) - Similarity
(Chinese) - Size
(Chinese) - State
(Chinese) - Style
(Chinese) - Text
(Chinese) - World Knowledge
(English Long) - 2D
(English Long) - 3D
(English Long) - Action-Overall
(English Long) - Animal
(English Long) - Attribute-Overall
(English Long) - Color
(English Long) - Comparison
(English Long) - Composition
(English Long) - Compound-Overall
(English Long) - Consistency
(English Long) - Contact
(English Long) - Expression
(English Long) - Feature matching
(English Long) - Full body
(English Long) - Grammar-Overall
(English Long) - Hand
(English Long) - Imagination
(English Long) - Inclusion
(English Long) - Layout-Overall
(English Long) - Logical Reasoning
(English Long) - Material
(English Long) - Negation
(English Long) - Non Contact
(English Long) - Overall
(English Long) - Pronoun Reference
(English Long) - Quantity
(English Long) - Relationship-Overall
(English Long) - Shape
(English Long) - Similarity
(English Long) - Size
(English Long) - State
(English Long) - Style
(English Long) - Text
(English Long) - World Knowledge
(English) - 2D
(English) - 3D
(English) - Action-Overall
(English) - Animal
(English) - Attribute-Overall
(English) - Color
(English) - Comparison
(English) - Composition
(English) - Compound-Overall
(English) - Consistency
(English) - Contact
(English) - Expression
(English) - Feature matching
(English) - Full body
(English) - Grammar-Overall
(English) - Hand
(English) - Imagination
(English) - Inclusion
(English) - Layout-Overall
(English) - Logical Reasoning
(English) - Material
(English) - Negation
(English) - Non Contact
(English) - Overall
(English) - Pronoun Reference
(English) - Quantity
(English) - Relationship-Overall
(English) - Shape
(English) - Similarity
(English) - Size
(English) - State
(English) - Style
(English) - Text
(English) - World Knowledge

Human preference

Data credits: LMArena, CC BY 4.0 (licence) · GenExam (OpenGVLab), MIT (licence) · UniGenBench++ (CodeGoat24), MIT (licence)

Around the web

  • Seedream 3.0 - ByteDance Seed
    April 16, 2025 Seedream 3.0 Next-Gen Text-to-Image Model We are officially launching Seedream 3.0, a …April 16, 2025 Seedream 3.0 Next-Gen Text-to-Image Model We are officially launching Seedream 3.0, a native high-resolution bilingual image generation foundational model (Chinese-English). Seedream 3…

    seed.bytedance.com

  • ByteDance Seed
    Section: > ByteDance Seed ... for ScienceRoboticsResponsible AI. Learn More. BlogSeed EdgeSeed Campus Recruitment. Models. …Section: > ByteDance Seed ... for ScienceRoboticsResponsible AI. Learn More. BlogSeed EdgeSeed Campus Recruitment. Models. Seed2.0 · Seedance 2.0 · Seedream 5.0 Lite · Seeduplex · Seed GR-RL. Section…

    seed.bytedance.com

  • Seedream 3.0 Text-to-Image Model Technical Report Released
    Seedream 3.0 Text-to-Image Model Technical Report Released Seedream 3.0 Text-to-Image Model Technical Report Released Date …Seedream 3.0 Text-to-Image Model Technical Report Released Seedream 3.0 Text-to-Image Model Technical Report Released Date 2025-04-16 Category Models ByteDance Seed team has officially released the t…

    seed.bytedance.com

  • Seedream 4.0 - Advanced AI Image Generation & Editing Platform | ByteDance
    with robust infrastructure designed for professional applications. The platform handles batch processing, API integration, and …with robust infrastructure designed for professional applications. The platform handles batch processing, API integration, and high-volume usage while maintaining consistent quality and performance a…

    seedream.one

  • Seedream 4.0 Officially Released: Beyond Drawing, Into Imagination
    diffusion models during fast sampling. Distribution matching : Instead of using a fixed Kullback-Leibler (KL) …diffusion models during fast sampling. Distribution matching : Instead of using a fixed Kullback-Leibler (KL) divergence, the ByteDance Seed team has introduced a learnable discriminator to improve t…

    seed.bytedance.com

  • Seedream - AI Image Generation Platform | ByteDance Free Trial | Seedance & Seedream
    Seedance 1.0 Seedance 1.5 Pro Seedance 2.0 Face Bypass Guide AI Video Guide Prompt Guide …Seedance 1.0 Seedance 1.5 Pro Seedance 2.0 Face Bypass Guide AI Video Guide Prompt Guide Seedream Seedream 3.0 Seedream 4.0 Seedream 4.5 Seedream 5.0 Compare Seedance vs Sora Seedance vs Runway Seeda…

    seedance2api.com

  • Seedream 4.0 by ByteDance on Vercel AI Gateway, Specs ...
    suits print layouts, hero imagery, and high-resolution editorial use without a separate upscaling step. ByteDance …suits print layouts, hero imagery, and high-resolution editorial use without a separate upscaling step. ByteDance reports a per-image generation time near 1.8 seconds in published examples, a meaning…

    vercel.com

  • Seedream 5.0 lite by ByteDance | Image Generation API
    image: https://og-api.replicateassets.com/api/models/bytedance/seedream-5-lite description: Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep …image: https://og-api.replicateassets.com/api/models/bytedance/seedream-5-lite description: Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowled…

    replicate.com

  • Seedream 5.0 lite by ByteDance | Image Generation API
    image: https://og-api.replicateassets.com/api/models/bytedance/seedream-5-lite description: Seedream 5.0 lite is ByteDance's image generation model with built-in reasoning, example-based …image: https://og-api.replicateassets.com/api/models/bytedance/seedream-5-lite description: Seedream 5.0 lite is ByteDance's image generation model with built-in reasoning, example-based editing, and…

    replicate.com

  • ByteDance Seedream 4.5: Text-to-Image AI Generator | fal
    Format · PNG via URL · Async by default, sync mode available for data URI …Format · PNG via URL · Async by default, sync mode available for data URI returns Technical Specifications Spec · Details Architecture · Seedream 4.5 Input Formats · Text prompts with detailed natura…

    fal.ai

Also known as: bytedance-seed/seedream-4.0, bytedance-seedream-v4-edit, bytedance/seedream-4, bytedance/seedream-4-0-250828, bytedance/seedream-4.0, bytedance/seedream-v4-edit, bytedance/seedream-v4-text-to-image, bytedance/seedream/v4/edit, bytedance/seedream/v4/text-to-image, doubao-seedream-4-0-250828, fal-ai/bytedance/seedream/v4/edit, fal-ai/bytedance/seedream/v4/text-to-image, replicate/bytedance/seedream-4, seedream-4, seedream-4-0, seedream-4-0-250828, seedream-4.0, seedream-4.0-2k, seedream-4.0-fal, seedream-4.0-high-res-fal, seedream-v4, seedream-v4-edit, together_ai/bytedance-seed/seedream-4.0

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works