ByteDance

Seedream 4.5

Name: Seedream 4.5
Brand: ByteDance
Price: 0.04 USD
Availability: InStock

AI Image Editing Model

Mode:

Image Featured #10 Text-to-Image #10 Image-to-Image

ByteDance's latest image generation model unifying text-to-image and image editing in a single architecture, with improved text rendering and 30-40% faster generation than v4.0

Seedream 4.5 generated image of A hyper-realistic close-up portrait of an elderly artisan woodworker in a sun...

Seedream 4.5 generated image of A hyper-realistic close-up of an elderly artisan’s weathered hands meticulous...

Try Model Benchmark examples

4096 x 4096

Max Resolution

Supported Modes

Text to Image Image Edit

Active

Details

Model ID

seedream-4.5

Also known as: seedream-4-5

Creator

ByteDance

Family

seedream

Released

December 2025

Ready to integrate?

Access seedream-4.5 via our unified API.

Create Account

Available at 3 providers

Starting from

$0.040 /image via BytePlus, fal.ai, Replicate

Prices shown are in USD

See all providers

Provider Performance

Fastest generation through fal at 22,022ms median latency with 100.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

fal

p95: 41,124ms

replicate

p95: 76,851ms

Success Rate

fal

100.0%

85 / 85 requests

replicate

73.3%

44 / 60 requests

Time to First Byte

fal

22,022ms

p95: 41,177ms

replicate

51,438ms

p95: 73,984ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	fal	22,022ms	41,124ms	100.0%	22,022ms
2	replicate	52,292ms	76,851ms	73.3%	51,438ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (3)

Seedream 4.5 is available from 3 providers, with per-image pricing starting at $0.04 through BytePlus.

BytePlus

Text to Image Image Edit

byteplus/seedream-4.5

Provider Model ID: seedream-4-5

$0.040 /image

View pricing details

fal.ai

Image Edit

fal/seedream-4.5-edit

Provider Model ID: fal-ai/bytedance/seedream/v4.5/edit

$0.040 /image

View pricing details

Replicate

Text to Image Image Edit

replicate/seedream-4.5

Provider Model ID: bytedance/seedream-4.5

$0.040 /image

View pricing details

seedream-4-5 API OpenAI-compatible

Integrate Seedream 4.5 via the Lumenfall OpenAI-compatible API to perform text-to-image generation and complex image editing through a single unified architecture.

Base URL

https://api.lumenfall.ai/openai/v1

Model

seedream-4.5

Code Examples

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=seedream-4.5" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'seedream-4.5',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="seedream-4.5",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for image generation	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") `auto` `1024x1024` WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") `auto` `1:1` Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `auto` `1K` Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

Output	`size`		`aspect_ratio` + `resolution`
Flexible
Auto	`"auto"`	—	Model chooses optimal dimensions
Custom 1–14142px per side	`"WxH"`	—	Any pixel dimensions within model constraints

1K 1 sizes

Output	`size`		`aspect_ratio` + `resolution`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format` byteplus	string	How generated images are returned. `b64_json` `url` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Additional Parameters

Provider-specific passthrough fields, available only when the request is routed to the listed provider.

Parameter	Type	Description	Modes
Universal
`prompt_enhancement`	string	Whether an LLM rewrites/expands the prompt before generation (off, on) `off` `on`	T2I Edit
`sequential_image_generation`	string	Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations). `disabled`	T2I Edit
byteplus
`sequential_image_generation_options`	object	Batch image generation options, effective only when sequential_image_generation is auto.	T2I Edit
`stream`	boolean	Whether to stream each output image as soon as it is generated.	T2I Edit
`watermark`	boolean	Whether to add an AI-generated watermark to the lower-right corner of the image.	T2I Edit
fal
`enable_safety_checker`	boolean	If set to true, the safety checker will be enabled.	T2I Edit
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	T2I Edit
replicate
`disable_safety_checker`	boolean	Disable the safety checker for generated images. When enabled, input moderation is relaxed to only block illegal content (CSAM). Use responsibly.	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Seedream 4.5 Benchmarks

Seedream 4.5 ranks as a top-ten global contender with an Elo of 1262 for text-to-image generation and 1211 for image editing. This ByteDance model demonstrates high competitive stability, holding the #8 position overall in text-to-image performance benchmarks.

Lumenfall Arena

#10

Text-to-Image

1260 Elo

Lumenfall Arena

#10

Image Editing

1209 Elo

Image Editing Landscape

Elo vs Cost

1 model without pricing omitted.

Competition Results

Image Editing

Photorealism

View leaderboard

Seedream 4.5 edited result for Golden Hour Stroll

Original image before Seedream 4.5 editing

Before After

Golden Hour Stroll

13 models

Image Editing

Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

#10

Man and Car in California

13 models

Image Editing

Source

Edit instruction

“Make a photo of the man driving the car down the California coastline”

Seedream 4.5 edited result for Bald man challenge

Before After

#10

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Seedream 4.5 edited result for Neutral Expression to Genuine Smile

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

3 attempts – showing best result

Seedream 4.5 edited result for Night Sky Transformation

Before After

#14

Night Sky Transformation

16 models

Image Editing

Edit instruction

“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”

3 attempts – showing best result

Image Editing

Anime

View leaderboard

Studio Ghibli Anime Style

14 models

Image Editing

Source

Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Image Editing

Portrait

View leaderboard

Before After

#10

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

3 attempts – showing best result

Uncategorized

Over-the-top cartoon caricature

13 models

Image Editing

Source

Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Top Matchups

See how Seedream 4.5 performs head-to-head against other AI models, ranked by community votes in blind comparisons.

Man and Car in California

Seedream 4.5 GPT Image 1.5

20% 80%

Modern Clean Menu

Seedream 4.5 Grok Imagine Image

0% 100%

Bald man challenge

Seedream 4.5 Nano Banana

0% 67%

Studio Ghibli Anime Style

Seedream 4.5 Nano Banana 2

33% 33%

Over-the-top cartoon caricature

Seedream 4.5 Nano Banana 2

50% 50%

Seedream 4.5 is best for

See all Use Cases

The model leads the industry in Anime and Photorealism categories, achieving first-place rankings with win rates of 77.3% and 80.0% respectively. It serves as a specialized tool for high-fidelity character art while maintaining a 57.9% win rate for commercial and branding applications.

#1 of 14

Anime

Edit · 66.7% win rate

#8 of 21

Photorealism

Edit · 45.7% win rate

Gallery

View all 7 images

Seedream 4.5 FAQ

How much does Seedream 4.5 cost?

Seedream 4.5 starts at $0.04 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use Seedream 4.5 via API?

You can use Seedream 4.5 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "seedream-4.5". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Seedream 4.5?

Seedream 4.5 is available through Replicate, fal.ai, and BytePlus on Lumenfall. Lumenfall automatically routes requests to the best available provider.

What is the maximum resolution for Seedream 4.5?

Seedream 4.5 supports images up to 4096x4096 resolution.

Overview

Seedream 4.5 is the latest image generation model developed by ByteDance, designed to bridge the gap between initial creation and iterative modification. It utilizes a unified architecture that handles both text-to-image synthesis and image editing tasks within the same framework, rather than relying on separate modular adapters. This version focuses specifically on increasing throughput and improving the legibility of embedded text compared to its predecessors.

Strengths

Unified Architecture: Unlike models that require specific Inpaint or Instruct-pix2pix checkpoints, Seedream 4.5 manages text-prompted generation and image-to-image editing natively in one model.
In-Image Typography: The model shows high accuracy in rendering complex text strings, logos, and labels within generated scenes, minimizing the common “gibberish” artifacts found in earlier diffusion iterations.
Generation Latency: ByteDance has optimized the inference pipeline to be 30-40% faster than Seedream 4.0, making it more viable for near-real-time applications and rapid prototyping.
Contextual Editing: Because it is designed for editing, the model excels at maintaining the global composition and lighting of an original image while adding, removing, or altering specific subjects via text instructions.

Limitations

Hardware Demand: While faster than version 4.0, the unified architecture still requires significant VRAM for high-resolution outputs compared to smaller, distilled models like SDXL Turbo.
Extreme Realism: While versatile, the model may still experience the “uncanny valley” effect in human anatomy—specifically hands and complex joint positions—where dedicated photorealism models may have a slight edge.
Prompt Sensitivity: To get the most out of the integrated editing features, users often need to provide highly specific instructions to prevent the model from over-altering the base image.

Technical Background

Seedream 4.5 is built on a latent diffusion framework that integrates multimodal inputs (text and reference images) directly into its primary denoising process. By training on a diverse dataset of paired editing sequences, the model learns to treat an input image as a soft spatial constraint rather than a rigid template. This allows for fluid transitions between “generating from scratch” and “modifying existing pixels” without switching model weights.

Best For

Seedream 4.5 is best suited for professional workflows where a user needs to generate a concept and then immediately iterate on specific details, such as changing a character’s clothing or adding a specific brand name to a storefront. It is an excellent choice for marketing teams building localized ad assets or developers building interactive design tools.

Seedream 4.5 is available for testing and deployment through Lumenfall’s unified API and playground, allowing you to integrate high-speed image generation and editing into your applications with a single integration.

Try Seedream 4.5 in Playground

Generate images with custom prompts — no API key needed.

Open Playground

Details

Ready to integrate?

Generation Time

Success Rate

Time to First Byte

Provider Rankings

Providers & Pricing (3)

Code Examples

Image Edit

Parameter Reference

Core Parameters

Size & Layout

How these parameters work

Priority when combined

How matching works

Media Inputs

Output & Format

Additional Parameters

Parameter Normalization

Seedream 4.5 Benchmarks

Image Editing Landscape

Elo vs Cost

Elo vs Speed

Competition Results

Photorealism

Anime

Portrait

Uncategorized

Top Matchups

Seedream 4.5 is best for

Gallery

Seedream 4.5 FAQ

Overview

Strengths

Limitations

Technical Background

Best For

Try Seedream 4.5 in Playground