# Seedream 4.5

> 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

## Quick Reference

- Model ID: seedream-4.5
- Creator: ByteDance
- Status: active
- Family: seedream
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 4096x4096
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/seedream-4.5?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for image generation. Modes: Text to Image, Image Edit
- `seed` (integer): Random seed for reproducibility. Modes: Text to Image, Image Edit

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: auto, 1024x1024. Modes: Text to Image, Image Edit
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: auto, 1:1. Modes: Text to Image, Image Edit
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: auto, 1K. Modes: Text to Image, Image Edit

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Text to Image, Image Edit
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Text to Image, Image Edit
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF). Modes: Text to Image, Image Edit
- `n` (integer): Number of images to generate. Default: 1. Modes: Text to Image, Image Edit

### Additional Parameters

- `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.. Modes: Text to Image, Image Edit. Only available via replicate
- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Modes: Text to Image, Image Edit. Only available via fal
- `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).. Values: disabled. Modes: Text to Image, Image Edit. Only available via replicate
- `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.. Modes: Text to Image, Image Edit. Only available via fal


## Model Identifiers

- Primary Slug: seedream-4.5
- Aliases: seedream-4-5


## Tags

image-generation, text-to-image, image-editing

## Available Providers

### BytePlus

- Config Key: byteplus/seedream-4.5
- Provider Model ID: seedream-4-5
- Pricing: $0.040/image
  - Source: https://docs.byteplus.com/en/docs/ModelArk/1544106

### fal.ai

- Config Key: fal/seedream-4.5
- Provider Model ID: fal-ai/bytedance/seedream/v4.5/text-to-image
- Pricing: $0.040/image
  - Source: https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/text-to-image

### fal.ai

- Config Key: fal/seedream-4.5-edit
- Provider Model ID: fal-ai/bytedance/seedream/v4.5/edit
- Pricing: $0.040/image
  - Source: https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/text-to-image

### Replicate

- Config Key: replicate/seedream-4.5
- Provider Model ID: bytedance/seedream-4.5
- Pricing: $0.040/image
  - Source: https://replicate.com/bytedance/seedream-4.5


## Performance Metrics

Provider performance over the last 30 days.

### fal

- Median Generation Time (p50): 24561ms
- 95th Percentile Generation Time (p95): 49356ms
- Average Generation Time: 27455ms
- Success Rate: 98.8%
- Total Requests: 241
- Time to First Byte (p50): 24402ms
- Time to First Byte (p95): 48984ms


## Arena Benchmarks

### Isometric Miniature Diorama Scenes

- Elo: 1269
- Record: 18W / 5L / 4T (27 battles)
- Rank: #1 of 21

### Golden Hour Stroll

- Elo: 1267
- Record: 31W / 7L / 1T (39 battles)
- Rank: #2 of 13

### Heroic Super Hero Portrait

- Elo: 1246
- Record: 12W / 5L / 1T (18 battles)
- Rank: #4 of 21

### Neutral Expression to Genuine Smile

- Elo: 1245
- Record: 17W / 10L / 2T (29 battles)
- Rank: #4 of 14

### Studio Ghibli Anime Style

- Elo: 1241
- Record: 22W / 10L / 1T (33 battles)
- Rank: #4 of 14

### Candid Street Photography

- Elo: 1221
- Record: 16W / 3L / 2T (21 battles)
- Rank: #2 of 24

### Man and Car in California

- Elo: 1218
- Record: 30W / 69L / 5T (104 battles)
- Rank: #10 of 13

### Apollo 11: Journey to Tranquility

- Elo: 1207
- Record: 12W / 9L / 0T (21 battles)
- Rank: #5 of 19

### Bald man challenge

- Elo: 1205
- Record: 16W / 10L / 5T (31 battles)
- Rank: #9 of 15

### Over-the-top cartoon caricature

- Elo: 1201
- Record: 19W / 13L / 4T (36 battles)
- Rank: #7 of 13

### Intricate Floral Mandala

- Elo: 1195
- Record: 14W / 9L / 1T (24 battles)
- Rank: #8 of 15

### Modern Clean Menu

- Elo: 1186
- Record: 8W / 11L / 3T (22 battles)
- Rank: #11 of 19

### Vintage Cafe Logo

- Elo: 1164
- Record: 12W / 8L / 2T (22 battles)
- Rank: #14 of 21

### Victorian Greenhouse Oasis

- Elo: 1154
- Record: 10W / 7L / 1T (18 battles)
- Rank: #15 of 17

### Night Sky Transformation

- Elo: 1152
- Record: 12W / 15L / 2T (29 battles)
- Rank: #14 of 16

### Adorable Baby Animals in Sunny Meadow

- Elo: 1148
- Record: 9W / 5L / 2T (16 battles)
- Rank: #17 of 25

### Geometric Composition

- Elo: 1055
- Record: 1W / 4L / 0T (5 battles)
- Rank: #22 of 22


## Use Cases & Category Performance

### Photorealism (Text-to-Image)

- Rank: #1 of 23
- Elo: 1262
- Record: 16W / 3L / 2T (21 battles)
- Win Rate: 76.2%

### Anime (Image Editing)

- Rank: #2 of 14
- Elo: 1225
- Record: 22W / 10L / 1T (33 battles)
- Win Rate: 66.7%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #8 of 21
- Elo: 1185
- Record: 12W / 8L / 2T (22 battles)
- Win Rate: 54.5%

### Text Rendering (Text-to-Image)

- Rank: #11 of 23
- Elo: 1229
- Record: 32W / 28L / 5T (65 battles)
- Win Rate: 49.2%

### Photorealism (Image Editing)

- Rank: #8 of 16
- Elo: 1223
- Record: 106W / 111L / 15T (232 battles)
- Win Rate: 45.7%

### Portrait (Image Editing)

- Rank: #8 of 15
- Elo: 1235
- Record: 33W / 20L / 7T (60 battles)
- Win Rate: 55.0%


## Image Gallery

22 images available for this model. Browse all at https://lumenfall.ai/models/bytedance/seedream-4.5/gallery

### Curated Examples

- [A grand, cinematic wide shot of a master calligrapher’s studio floating in a celestial void, wher...](https://assets.lumenfall.ai/GZ8FwPp_IFMxh_1yZAJpbwJjud0sf-q1HLt0VQWNsY4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/w2q4k1n2by00qp3ag5f6wjj0avvl@jpeg)
- [A cinematic, wide 16:9 shot of a high-end coastal boutique hotel at dusk. The building features w...](https://assets.lumenfall.ai/iFpzSafyNRM-IT9fU-dpix_oZnCq3IJokrxwBiS9_dE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/9zffkshawhwiudgwvhf22uiduyma@jpeg)
- [A hyper-realistic close-up portrait of an elderly artisan woodworker in a sun-drenched workshop. ...](https://assets.lumenfall.ai/8tpeDsdC894eviWUw245DUH_cQtVPo4JZZ5fWzj-u58/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/se5o1vivcr2we0s1ks7xqp0hiwwb@jpeg)
- [A hyper-realistic close-up of an elderly artisan’s weathered hands meticulously carving a delicat...](https://assets.lumenfall.ai/rcxmRaNIIHagGEvupDh6amejI_LWOsOsMGMDimGUZzI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/h4qvxmxkjryishujlsnokq9iexfk@jpeg)
- [A vibrant, hand-painted wooden sign for a "SUNSET BAKERY" hanging over a cozy storefront. The typ...](https://assets.lumenfall.ai/53ZsMCY93D1vfJUAVt1Rc7-vym11H1d_pdd4osXVmt8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/8kazwokrrk04frs1zjf4sey4pltc@jpeg)

### Arena Competition Results

- [Isometric Miniature Diorama Scenes](https://assets.lumenfall.ai/tIgVYoMqwfk45FEqHyhrd0ju7S6JaDYeMU3LVc0U4mA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/x500dd5bvmy6ys3puhsnx48t85bc@jpeg): #1 of 21 (Elo 1269)
- [Golden Hour Stroll](https://assets.lumenfall.ai/HGEjJFnMjbO6H7e9L3PTKtnxhmoYJD5OeNdz9svq9kE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/n29b62le5hui9swg8fvrsqmoalln@jpeg): #2 of 13 (Elo 1267)
- [Heroic Super Hero Portrait](https://assets.lumenfall.ai/YrRtmUxt5ymStTBnBF685b6NbkN5MlPX2q5wJK2vZWY/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/z27kr2zptlkbqpfcebkjmu8c5m77@jpeg): #4 of 21 (Elo 1246)
- [Neutral Expression to Genuine Smile](https://assets.lumenfall.ai/QmeoXNpOJzevI4XkZIcyCvifIm79fhYCdS2w_PMivGI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/urtazajh7o3hds94iyzjd5b4ayjh@jpeg): #4 of 14 (Elo 1245)
- [Studio Ghibli Anime Style](https://assets.lumenfall.ai/CPaI-RsFzs2Y0OjhOs0-Nuiq3H442xyUOsmCmQ1NUvc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/f4qgtra5lxz7s140nknuduupa6wj@jpeg): #4 of 14 (Elo 1241)
- [Candid Street Photography](https://assets.lumenfall.ai/7VOu-BDhVnhOMTAXnfHTUIKqO8edsO_TNKa_DbPbQgM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/jkwlehpy38zi287fuykty2bi89eu@jpeg): #2 of 24 (Elo 1221)
- [Man and Car in California](https://assets.lumenfall.ai/LNYTsaU1QqyDxk0yrXHRkeCsMIt8rd525i9m7BOfApQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/v2tzlgf44ymo83lgh9nn57m0yznd@jpeg): #10 of 13 (Elo 1218)
- [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/1HK8GwiIJba7aNc7b4lLVNcn6m1UR4-itZ7RXf5FD4s/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/snwinhvxzi79kznoa20na03l0dnf@jpeg): #5 of 19 (Elo 1207)
- [Bald man challenge](https://assets.lumenfall.ai/yZTwuaCBr0gFSbzQSvdi5erOxFfUNelzxJdkbXisTpk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/81alr1gfybqvs2e84pjc55fzsupv@jpeg): #9 of 15 (Elo 1205)
- [Over-the-top cartoon caricature](https://assets.lumenfall.ai/LBJjZ5p79qPDgTY-TSzsQH7LCRkxe4b_n8RUwjyfO4I/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/y3jsfonmoof3zr48snbolbzh61eq@jpeg): #7 of 13 (Elo 1201)
- [Intricate Floral Mandala](https://assets.lumenfall.ai/2f6I2DsfkEV6hWJyM30hr5KjirrEgVVhIxwb9YKVOuc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/44n01ekr6us0c4w3f676ligb2nkd@jpeg): #8 of 15 (Elo 1195)
- [Modern Clean Menu](https://assets.lumenfall.ai/QupHx__ILdZ-nxrJgXonTN0YALuyq68tMxbGtuAII9g/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/8idgmaeh1fellirzvgi0gym71cs7@jpeg): #11 of 19 (Elo 1186)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/9ZACaAuz5SeI_1IQLeaWI0GcUqZ79LPd87ogoTaQJXU/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/x12yd2eofqjjnzuv1c1ykp6sc8nr@jpeg): #14 of 21 (Elo 1164)
- [Victorian Greenhouse Oasis](https://assets.lumenfall.ai/wi9PCnU68YqETk4Sfan9gsk2PnwcgDMfRuq1-bK8DgU/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/w2qao527u1ns5cffwh4bdc6ltxa3@jpeg): #15 of 17 (Elo 1154)
- [Night Sky Transformation](https://assets.lumenfall.ai/b1GaC3q9SRYCEO4DdUwzQLbDcXYW3PgDtsJjkvloOZM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/5w8b2u4ooyvt18oe4qzu8x14vkrf@jpeg): #14 of 16 (Elo 1152)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/SUtE3hvOmZfwIl-PtrnIvYXYk5lZ1GDSNvaMtFMIGZg/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/2b7vbfjdzea4pb0kkl8pviyivuv3@jpeg): #17 of 25 (Elo 1148)
- [Geometric Composition](https://assets.lumenfall.ai/gmw3g-80J3K_TgcBpkAe2PCwEgOyclG2e5A6p3PtI9U/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/iuq11nlc8vq6owu2g2uor23fwbom@jpeg): #22 of 22 (Elo 1055)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A vibrant, hand-painted wooden sign for a "SUNSET BAKERY" hanging over a cozy storefront. The typography is elegant gold leaf script. In the soft-focus background, a capybara sits peacefully on the sidewalk, nibbling on a stray baguette.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-4.5",
    "prompt": "",
    "size": "1024x1024"
  }'

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

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'seedream-4.5',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="seedream-4.5",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=seedream-4.5" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

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

#### JavaScript

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);

#### Python

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)


## About

## 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.

## Frequently Asked Questions

### 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 BytePlus, fal.ai, and Replicate 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.

## Links

- Model Page: https://lumenfall.ai/models/bytedance/seedream-4.5
- About: https://lumenfall.ai/models/bytedance/seedream-4.5/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/bytedance/seedream-4.5/providers
- API Reference: https://lumenfall.ai/models/bytedance/seedream-4.5/api
- Benchmarks: https://lumenfall.ai/models/bytedance/seedream-4.5/benchmarks
- Use Cases: https://lumenfall.ai/models/bytedance/seedream-4.5/use-cases
- Gallery: https://lumenfall.ai/models/bytedance/seedream-4.5/gallery
- Playground: https://lumenfall.ai/playground?model=seedream-4.5
- API Documentation: https://docs.lumenfall.ai