# Seedream 4.0

> ByteDance's image generation model with integrated text-to-image and image editing capabilities in a unified architecture, supporting up to 4K resolution

## Quick Reference

- Model ID: seedream-4
- 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?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, 1563x670, 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1183x887. Modes: Text to Image, Image Edit
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: auto, 9:16, 2:3, 3:4, 1:1, 4:3, 3:2, 16:9, 21:9. 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 generated images are returned.. Default: url. Values: b64_json, url. Modes: Text to Image, Image Edit. Only available via byteplus
- `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

- `prompt_enhancement` (string): Whether an LLM rewrites/expands the prompt before generation (off, on). Values: off, on. Modes: Text to Image, Image Edit
- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Modes: Text to Image, Image Edit. Only available via fal
- `height` (integer): Custom image height (only used when size='custom'). Range: 1024-4096 pixels.. Modes: Text to Image, Image Edit. Only available via replicate
- `sequential_image_generation` (string): Controls batch image generation; `disabled` returns one image and `auto` lets the model decide whether and how many images to return.. Values: disabled. Modes: Text to Image, Image Edit
- `sequential_image_generation_options` (object): Batch image generation options, effective only when sequential_image_generation is auto.. Modes: Text to Image, Image Edit. Only available via byteplus
- `stream` (boolean): Whether to stream each output image as soon as it is generated.. Modes: Text to Image, Image Edit. Only available via byteplus
- `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
- `watermark` (boolean): Whether to add an AI-generated watermark to the lower-right corner of the image.. Modes: Text to Image, Image Edit. Only available via byteplus
- `width` (integer): Custom image width (only used when size='custom'). Range: 1024-4096 pixels.. Modes: Text to Image, Image Edit. Only available via replicate


## Model Identifiers

- Primary Slug: seedream-4
- Aliases: seedream-4.0

## Dates

- Released: September 2025

## Tags

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

## Available Providers

### BytePlus

- Config Key: byteplus/seedream-4
- Provider Model ID: seedream-4-0
- Pricing: $0.030/image
  - Source: https://docs.byteplus.com/en/docs/ModelArk/1544106

### fal.ai

- Config Key: fal/seedream-4
- Provider Model ID: fal-ai/bytedance/seedream/v4/text-to-image
- Pricing: $0.030/image
  - Source: https://fal.ai/models/fal-ai/bytedance/seedream/v4/text-to-image

### fal.ai

- Config Key: fal/seedream-4-edit
- Provider Model ID: fal-ai/bytedance/seedream/v4/edit
- Pricing: $0.030/image
  - Source: https://fal.ai/models/fal-ai/bytedance/seedream/v4/text-to-image

### Replicate

- Config Key: replicate/seedream-4
- Provider Model ID: bytedance/seedream-4
- Pricing: $0.030/image
  - Source: https://replicate.com/bytedance/seedream-4


## Performance Metrics

Provider performance over the last 30 days.

### fal

- Median Generation Time (p50): 13448ms
- 95th Percentile Generation Time (p95): 43096ms
- Average Generation Time: 20655ms
- Success Rate: 100.0%
- Total Requests: 14
- Time to First Byte (p50): 13661ms
- Time to First Byte (p95): 40184ms


## Arena Benchmarks

### Victorian Greenhouse Oasis

- Elo: 1242
- Record: 16W / 9L / 0T (25 battles)
- Rank: #4 of 17

### Isometric Miniature Diorama Scenes

- Elo: 1240
- Record: 14W / 19L / 1T (34 battles)
- Rank: #8 of 72

### Geometric Composition

- Elo: 1224
- Record: 16W / 12L / 3T (31 battles)
- Rank: #9 of 70

### Adorable Baby Animals in Sunny Meadow

- Elo: 1219
- Record: 12W / 7L / 1T (20 battles)
- Rank: #8 of 72

### Studio Ghibli Anime Style

- Elo: 1214
- Record: 23W / 13L / 0T (36 battles)
- Rank: #10 of 46

### Night Sky Transformation

- Elo: 1209
- Record: 16W / 11L / 2T (29 battles)
- Rank: #8 of 16

### Over-the-top cartoon caricature

- Elo: 1200
- Record: 12W / 24L / 0T (36 battles)
- Rank: #6 of 44

### Candid Street Photography

- Elo: 1181
- Record: 12W / 8L / 1T (21 battles)
- Rank: #17 of 68

### Apollo 11: Journey to Tranquility

- Elo: 1179
- Record: 9W / 11L / 0T (20 battles)
- Rank: #13 of 70

### Vintage Cafe Logo

- Elo: 1177
- Record: 17W / 20L / 0T (37 battles)
- Rank: #13 of 70

### Neutral Expression to Genuine Smile

- Elo: 1173
- Record: 12W / 17L / 6T (35 battles)
- Rank: #13 of 14

### Modern Clean Menu

- Elo: 1161
- Record: 4W / 22L / 1T (27 battles)
- Rank: #20 of 69

### Heroic Super Hero Portrait

- Elo: 1146
- Record: 12W / 18L / 0T (30 battles)
- Rank: #17 of 21

### Intricate Floral Mandala

- Elo: 1144
- Record: 6W / 11L / 2T (19 battles)
- Rank: #13 of 15

### The Halloween Invitation

- Elo: 1141
- Record: 2W / 3L / 0T (5 battles)
- Rank: #7 of 70

### Golden Hour Stroll

- Elo: 1135
- Record: 7W / 24L / 0T (31 battles)
- Rank: #14 of 45

### Man and Car in California

- Elo: 1134
- Record: 4W / 87L / 1T (92 battles)
- Rank: #14 of 35

### Bald man challenge

- Elo: 1122
- Record: 5W / 32L / 2T (39 battles)
- Rank: #17 of 43

### Selective Object Swap

- Elo: 1063
- Record: 1W / 2L / 1T (4 battles)
- Rank: #4 of 12


## Use Cases & Category Performance

### Photorealism (Text-to-Image)

- Rank: #10 of 61
- Elo: 1218
- Record: 42W / 27L / 3T (72 battles)
- Win Rate: 58.3%

### Aesthetics (Text-to-Image)

- Rank: #17 of 62
- Elo: 1238
- Record: 78W / 91L / 5T (174 battles)
- Win Rate: 44.8%

### Creativity (Text-to-Image)

- Rank: #17 of 56
- Elo: 1222
- Record: 43W / 53L / 1T (97 battles)
- Win Rate: 44.3%

### Prompt Adherence (Text-to-Image)

- Rank: #20 of 60
- Elo: 1230
- Record: 57W / 71L / 4T (132 battles)
- Win Rate: 43.2%

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

- Rank: #20 of 58
- Elo: 1216
- Record: 47W / 75L / 2T (124 battles)
- Win Rate: 37.9%

### 3D Imaging & Modeling (Text-to-Image)

- Rank: #11 of 29
- Elo: 1231
- Record: 30W / 31L / 2T (63 battles)
- Win Rate: 47.6%

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

- Rank: #21 of 56
- Elo: 1209
- Record: 33W / 56L / 1T (90 battles)
- Win Rate: 36.7%

### Artistic Restyling (Image Editing)

- Rank: #9 of 15
- Elo: 1203
- Record: 35W / 37L / 0T (72 battles)
- Win Rate: 48.6%

### Creativity (Image Editing)

- Rank: #9 of 15
- Elo: 1203
- Record: 35W / 37L / 0T (72 battles)
- Win Rate: 48.6%

### Preservation (Image Editing)

- Rank: #19 of 29
- Elo: 1162
- Record: 63W / 199L / 8T (270 battles)
- Win Rate: 23.3%

### Photorealism (Image Editing)

- Rank: #18 of 26
- Elo: 1171
- Record: 43W / 171L / 9T (223 battles)
- Win Rate: 19.3%

### Art (Text-to-Image)

- Rank: #17 of 24
- Elo: 1137
- Record: 3W / 3L / 0T (6 battles)
- Win Rate: 50.0%

### Lighting, Shadows & Materials (Image Editing)

- Rank: #20 of 28
- Elo: 1172
- Record: 31W / 154L / 5T (190 battles)
- Win Rate: 16.3%

### Prompt Adherence (Image Editing)

- Rank: #16 of 22
- Elo: 1187
- Record: 13W / 27L / 1T (41 battles)
- Win Rate: 31.7%

### Face & Identity (Image Editing)

- Rank: #13 of 16
- Elo: 1171
- Record: 28W / 72L / 6T (106 battles)
- Win Rate: 26.4%

### Backgrounds & Scenes (Image Editing)

- Rank: #15 of 16
- Elo: 1191
- Record: 20W / 98L / 3T (121 battles)
- Win Rate: 16.5%

### Aesthetics (Image Editing)

- Rank: #15 of 16
- Elo: 1171
- Record: 34W / 124L / 1T (159 battles)
- Win Rate: 21.4%

### People & Poses (Image Editing)

- Rank: #17 of 18
- Elo: 1122
- Record: 7W / 24L / 0T (31 battles)
- Win Rate: 22.6%

### Adding & Editing Objects (Image Editing)

- Rank: #19 of 19
- Elo: 1097
- Record: 5W / 90L / 2T (97 battles)
- Win Rate: 5.2%


## Image Gallery

23 images available for this model. Browse all at https://lumenfall.ai/models/bytedance/seedream-4/gallery

### Curated Examples

- [Cinematic wide shot of a high-end, boutique camera store at twilight. The shop window features a ...](https://assets.lumenfall.ai/ati1n39qdiz4OV2NtZuWfU-E57iBd0Kf80exqvsQYyk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/uxvsgv4d1g1q613d08kg03lro8sz@jpeg)
- [A hyper-realistic close-up of an artisan watchmaker's desk, scattered with intricate brass gears,...](https://assets.lumenfall.ai/8HtlHrR9qaQh74V26DfeTaR0PA-8Eg4Ls4wggnoYQ6A/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/x32mbi6wjdvbtwg8u8tvidc7xoh1@jpeg)
- [A hyper-realistic close-up of an artisan watchmaker's workbench, shallow depth of field focusing ...](https://assets.lumenfall.ai/rU9pEkTsSiTEL8-S7IA57W5LpB7ly4OEIxUMsQEE0kM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/0oe03ng366jy67prf5fo9smfkhmk@jpeg)
- [A sunlit, minimalist florist shop with a large chalkboard sign that reads "BLOOMS & BEYOND" in el...](https://assets.lumenfall.ai/bEyLUKa__p7WbSZPoHwmgdx0SAw7Kp8HiFJMPKhL0Cc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ox2g1bognvegqbitbpbu0dnz9kuh@jpeg)

### Arena Competition Results

- [Victorian Greenhouse Oasis](https://assets.lumenfall.ai/DJCrw9l0Gk2HyDCrpTb2bb3NVVStsh5m58Y9xDsOrJs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/o54p33z4dgzu7zpsga5s29vjjh3i@jpeg): #4 of 17 (Elo 1242)
- [Isometric Miniature Diorama Scenes](https://assets.lumenfall.ai/JfvVqvN334kyl_UmERfE9TcnIkJzRXk0kSkMpp81Kzg/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/c6mq6bfn7du2kovdu4zndsj0btqn@jpeg): #8 of 72 (Elo 1240)
- [Geometric Composition](https://assets.lumenfall.ai/tS6oSpjN53hrs9z_ejUpDir47fhosc385J0K0IKx2tU/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/gpivmw7ueebmtq846fb3w2b5v6cz@jpeg): #9 of 70 (Elo 1224)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/1K4gxI8ZgyCZ5pPypMVURssFWwSLsTG_lnIDg3gsci8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/13z2zusrns1ejnf67jjy0nmr536b@jpeg): #8 of 72 (Elo 1219)
- [Studio Ghibli Anime Style](https://assets.lumenfall.ai/9uxk-lVebrNBb6kidxl6aFQEXDuyx0MjbFaHnrF1ANk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/w59b9r1f7tdoaa69xdzqerc1n8ml@jpeg): #10 of 46 (Elo 1214)
- [Night Sky Transformation](https://assets.lumenfall.ai/8V4RG17dNYZ5x99E42_aGG_kDz2z24OhDrjeSXWTBV0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/mz8jzjx4t1fzoc87bbrxgtnffl7j@jpeg): #8 of 16 (Elo 1209)
- [Over-the-top cartoon caricature](https://assets.lumenfall.ai/VS-Mvvl5yDD1MibWHIKCntz2iMFejIesxWuN0RUG49U/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/2dvo3jzhcfs0xtljmjj0zrk9fwp4@jpeg): #6 of 44 (Elo 1200)
- [Candid Street Photography](https://assets.lumenfall.ai/6HXdQZ12D4XR9_Surb4W5K1y648YzW-I_Hdnbu7rqHM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/b1hjrwmwfiveosyjkxg7474chith@jpeg): #17 of 68 (Elo 1181)
- [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/boMv7lUiGWfzCqWFspwqGunPmd7LthsObpXsH8mtzNs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/h1gegmq04bswpcwz0pslft77y3a5@jpeg): #13 of 70 (Elo 1179)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/u574JjiR3fR0MLwg9GrmL3mm_N3vf-MrnazA9Ufgc54/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/hb23pe5n1yaotpjr3i1o5z0ggxik@jpeg): #13 of 70 (Elo 1177)
- [Neutral Expression to Genuine Smile](https://assets.lumenfall.ai/Jaz5JtPdFAEa-uJ-wbYPuxiSXoZeO-kAlC1_jjIAtao/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/8eaucnx4bukx6ei542uagn2at97j@jpeg): #13 of 14 (Elo 1173)
- [Modern Clean Menu](https://assets.lumenfall.ai/fJlKnnMsGpS7gC_tW_bbFErIunPqNdP_4ILI_mQOvA0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/eourxtg20r2jxvmuet1l5fkpywsv@jpeg): #20 of 69 (Elo 1161)
- [Heroic Super Hero Portrait](https://assets.lumenfall.ai/zW3P3WU1D6C7HMRNIQYQiOCTva0mxR7NzzX13mIJTBs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/23ezwkiq38j05e09r167q6y6uaj7@jpeg): #17 of 21 (Elo 1146)
- [Intricate Floral Mandala](https://assets.lumenfall.ai/o-s_v_aJ1HFa_Fxt3qqURfXIfGVUI_99so1G45zvR-E/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/7szunabqfwg7vnqis61znlwyns0z@jpeg): #13 of 15 (Elo 1144)
- [The Halloween Invitation](https://assets.lumenfall.ai/V3iyoZHJ87Syi0qsyWeN_WUXBK276-3ZsvhMpdvrMUc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/zls9ubr125h0p6b452ng5fhnw24r@jpeg): #7 of 70 (Elo 1141)
- [Golden Hour Stroll](https://assets.lumenfall.ai/U900fZ_21tPFxQ4bIgtY4F6B9yRZpYi0L8ck68M3epo/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ex62y8e3q84r0e8he5lwiwprejhz@jpeg): #14 of 45 (Elo 1135)
- [Man and Car in California](https://assets.lumenfall.ai/l3qSBOJERyC4_NUlGxI33WoTJNkxqZOOolPvmw6PypQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/6q9uqdnrb452snqzf3dntja71igl@jpeg): #14 of 35 (Elo 1134)
- [Bald man challenge](https://assets.lumenfall.ai/iVPBBDzg0nN4yq1i1V5sJUqiFR9GjAH4QG-3izBmzvQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/u7x3o85spwvwkyxgq0gl37zgbz40@jpeg): #17 of 43 (Elo 1122)
- [Selective Object Swap](https://assets.lumenfall.ai/ksFiQuepn0FyAbDR79PrW3FQ5HheieKL7Xx8C9hMsxw/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/a8vn5kl5i3zvjaj61xvbo7onugob@jpeg): #4 of 12 (Elo 1063)

## Example Prompt

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

A sunlit, minimalist florist shop with a large chalkboard sign that reads "BLOOMS & BEYOND" in elegant cursive. A variety of colorful tulips are in the foreground. In the blurry background, a capybara calmly rests on a terracotta floor tile.

## 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",
    "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',
  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",
    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" \
  -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',
  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",
    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 4.0 is a high-resolution image generation and editing model developed by ByteDance. It utilizes a unified architecture that handles both text-to-image synthesis and sophisticated image manipulation within the same framework. This version is specifically designed for high-fidelity outputs, supporting image generation at resolutions up to 4K.

## Strengths
*   **High-Resolution Output:** Demonstrates superior performance in generating 4K imagery, maintaining sharpness and fine textures that often degrade in standard 1024px models.
*   **Unified Task Processing:** Unlike models that require separate adapters (like ControlNet) for editing, Seedream 4.0 integrates generation and editing capabilities into a single pipeline, improving consistency between original and edited pixels.
*   **Multi-Modal Conditioning:** Processes both text prompts and image inputs simultaneously, allowing for precise instruction-following when modifying existing compositions or styles.
*   **Instruction Adherence:** Shows high accuracy in translating complex descriptive prompts into visual elements, particularly in maintaining spatial relationships between objects.

## Limitations
*   **Inference Latency:** Generating at 4K resolution requires significant computational resources, leading to slower generation times compared to lower-resolution models like SDXL or Flux Schnell.
*   **Operational Cost:** At a starting price of $0.03 per generation, it carries a higher cost-per-image than many base latent diffusion models, making it less ideal for high-volume batch processing of simple assets.
*   **Prompt Sensitivity:** While capable of high fidelity, the model’s unified architecture may occasionally require more specific prompting to distinguish between "generate new content" and "preserve existing content" during editing tasks.

## Technical Background
Seedream 4.0 is built on an evolution of ByteDance’s diffusion research, moving away from fragmented architectures toward a unified sequence-to-sequence approach for visual tasks. It treats image editing and generation as a singular objective, which likely involves a high-capacity transformer-based backbone optimized for large-scale spatial parameters. The training regimen emphasizes high-resolution data scaling to ensure the model maintains coherence at 4K dimensions.

## Best For
Seedream 4.0 is ideal for professional design workflows where high-print quality or large-format digital assets are required. It excels in scenarios involving "inpainting" and complex image-to-image transformations where the user needs to maintain the integrity of a base image while adding specific details.

Seedream 4.0 is available through **Lumenfall’s unified API and playground**, allowing developers to integrate its 4K generation and editing capabilities without managing complex infrastructure.

## Frequently Asked Questions

### How much does Seedream 4.0 cost?

Seedream 4.0 starts at $0.03 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Seedream 4.0 via API?

You can use Seedream 4.0 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "seedream-4". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Seedream 4.0?

Seedream 4.0 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 4.0?

Seedream 4.0 supports images up to 4096x4096 resolution.

## Links

- Model Page: https://lumenfall.ai/models/bytedance/seedream-4
- About: https://lumenfall.ai/models/bytedance/seedream-4/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/bytedance/seedream-4/providers
- API Reference: https://lumenfall.ai/models/bytedance/seedream-4/api
- Benchmarks: https://lumenfall.ai/models/bytedance/seedream-4/benchmarks
- Use Cases: https://lumenfall.ai/models/bytedance/seedream-4/use-cases
- Gallery: https://lumenfall.ai/models/bytedance/seedream-4/gallery
- Playground: https://lumenfall.ai/models/bytedance/seedream-4/playground
- API Documentation: https://docs.lumenfall.ai