AI Image Editing Model
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
Starting from
Prices shown are in USD
See all providersFastest generation through fal at 22,180ms median latency with 100.0% success rate.
Aggregated from real API requests over the last 30 days.
| # | Provider | p50 Gen Time | p95 Gen Time | Success Rate | TTFB (p50) |
|---|---|---|---|---|---|
| 1 | fal | 22,180ms | 42,988ms | 100.0% | 22,290ms |
Seedream 4.5 is available from 3 providers, with per-image pricing starting at $0.04 through BytePlus.
byteplus/seedream-4.5
fal/seedream-4.5
replicate/seedream-4.5
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.
https://api.lumenfall.ai/openai/v1
seedream-4.5
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": "..." }] }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);from openai import OpenAIclient = 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)| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
Edit
|
seed
|
integer | Random seed for reproducibility |
T2I
Edit
|
| 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 |
| Output |
size
|
aspect_ratio
+
resolution
|
|
|---|---|---|---|
| 1024 × 1024 | "1024x1024" |
or |
"1:1"
+
"1K"
|
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
| Parameter | Type | Description | Modes |
|---|
| 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:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
Edit
|
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
|
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.
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.
“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
“Hyper-photorealistic full-body portrait of a female superhero standing triumphantly on a New York skyscraper rooftop at golden sunset, wearing a classic modest superhero costume with flowing cape, chest emblem, gloves, and boots in red and blue colors, practical design, short hair, strong determined heroic expression looking into the distance, powerful confident stance with hands on hips and cape billowing dramatically in the wind, detailed urban cityscape background, warm natural sunlight with sharp shadows and fabric highlights, ultra-sharp textures on suit, hair, and concrete, 8K masterpiece, empowering family-friendly style.”
“Perfectly symmetrical mandala made entirely of real flowers, petals, leaves, fruits, and seeds in vibrant natural colors, intricate layered patterns with radial symmetry, top-down view on a soft neutral background, hyper-detailed organic textures and subtle shadows, photorealistic, 8K masterpiece.”
“Hyper-photorealistic interior of a lush Victorian glass greenhouse filled with exotic tropical plants, vibrant blooming orchids, tall ferns, colorful butterflies in flight, sunlight filtering through ornate glass roof creating realistic caustics and dew on leaves, intricate iron framework visible, misty atmosphere, 8K masterpiece.”
See how Seedream 4.5 performs head-to-head against other AI models, ranked by community votes in blind comparisons.
vs Nano Banana Pro
Challenge: Man and Car in California
0% W · 100% L
vs Grok Imagine Image
Challenge: Modern Clean Menu
0% W · 100% L
vs Nano Banana
Challenge: Bald man challenge
0% W · 67% L · 33% T
vs FLUX.2 [max]
Challenge: Studio Ghibli Anime Style
33% W · 67% L
vs Nano Banana 2
Challenge: Over-the-top cartoon caricature
50% W · 50% L
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.
Seedream 4.5 starts at $0.04 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
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.
Seedream 4.5 is available through Replicate, fal.ai, and BytePlus on Lumenfall. Lumenfall automatically routes requests to the best available provider.
Seedream 4.5 supports images up to 4096x4096 resolution.
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.
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.
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.
Generate images with custom prompts — no API key needed.
