Seedream 4.5 API
ByteDance Seedream 4.5 — fast, affordable image generation and editing with best-in-class CJK text rendering and strong instruction adherence on complex prompts.

About the Seedream 4.5 API
What Seedream 4.5 does, how it fits in the ByteDance model lineup, and why teams reach for it.
Seedream 4.5 is a image generation and editing model from ByteDance, available through the WaveSpeedAI REST API. ByteDance Seedream 4.5 — fast, affordable image generation and editing with best-in-class CJK text rendering and strong instruction adherence on complex prompts.
The Seedream 4.5 family on WaveSpeedAI ships 4 REST endpoints covering Text-To-Image, Image-To-Image workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Seedream 4.5 through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Seedream 4.5 API endpoints
4 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Sequential
Seedream 4.5 Sequential generates multi-image sets with consistent characters and objects, unifying palette, lighting, and style across all outputs. Supports up to 4K results for campaigns, storyboards, and product lines. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedream v4.5
Seedream 4.5 is a next-gen text-to-image model optimized for typography—crisper text rendering, stronger prompt adherence, and up to 4K output for posters and brand visuals. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Edit Sequential
Seedream 4.5 Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Edit
Seedream 4.5 Edit preserves facial features, lighting, and color tone from reference images, delivering professional, high-fidelity edits up to 4K with strong prompt adherence. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
See Seedream 4.5 in action
Real outputs generated by the Seedream 4.5 API. Hover any video to preview, click to open the full-size viewer.
How to use the Seedream 4.5 API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from "queued" or "processing" to "completed".
- 4
Read the output URL
Once status is "completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Seedream 4.5 variant you called.
What you can build with Seedream 4.5
Common workflows developers and creators use the Seedream 4.5 API for.
High-volume image generation
Best $/image at production scale for general-purpose generation — strong default for ad creative, social, and editorial pipelines that need thousands of outputs per day.
CJK / Asian-language imagery
Top-tier Chinese, Japanese, and Korean text rendering, with cultural context (calligraphy styles, regional fashion, traditional architecture) that Western-trained models miss.
E-commerce product imagery
Fast iteration on product variants — model the same SKU in different settings, lighting, and contexts at a fraction of stock-photo licensing cost.
Storyboard panel generation
Generate consistent panels for storyboards, comics, and scene previz — instruction following is strong enough to maintain pose/composition across frames.
Brand exploration and logo concepts
Early-stage brand and logo exploration — wide style coverage at a price point that makes 100+ exploratory generations cheap.
Tips for prompting Seedream 4.5
Practical advice for getting better outputs from Seedream 4.5 — drawn from the patterns that work across image models in production pipelines.
Describe lighting, composition, and style — not just subject
Move past 'a cat' to 'a tabby cat on a windowsill, soft afternoon light streaming in, shallow depth of field, cinematic 35mm composition'. Subject + scene + lighting + camera language is the prompt formula that pulls best from image-model training data.
Use style anchors instead of artist names
'In the style of editorial photography' or 'studio product shot, white seamless background' beats vague 'high quality, masterpiece' boilerplate AND avoids the legal / licensing concerns that come with naming living artists in commercial work.
Specify resolution and aspect ratio explicitly
Don't rely on defaults. Set the target aspect ratio (1:1, 4:3, 16:9) and resolution up front. Cropping or upscaling later loses fidelity that the model could have placed correctly in the first generation.
Iterate on a locked seed before re-rolling
Lock the seed, change one prompt element at a time. Much faster than re-rolling random seeds for every change — you isolate cause-and-effect on each prompt edit and reach the target image with fewer total generations.
Use the edit endpoint for refinements, not full re-generation
Generate the base image once, then use the model's edit / inpaint endpoint to refine specific elements — text, lighting, individual subjects. Edits preserve everything you liked about the base and cost less per iteration than full re-generations.
Seedream 4.5 API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| bytedance/seedream-v4.5/sequential | text-to-image | $0.040 |
| bytedance/seedream-v4.5 | text-to-image | $0.040 |
| bytedance/seedream-v4.5/edit-sequential | image-to-image | $0.040 |
| bytedance/seedream-v4.5/edit | image-to-image | $0.040 |
Call the Seedream 4.5 API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("bytedance/seedream-v4.5", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedream-v4.5",
{}
)
print(output["outputs"][0]) # → URL of the generated outputSeedream 4.5 vs alternatives
When to pick Seedream 4.5 over similar models on WaveSpeedAI.
Seedream 4.5 vs Seedream 5 Lite
Seedream 5 Lite is the newer cost-optimized tier — about half the price and faster. 4.5 still has the edge on complex instruction adherence and multi-element compositions.
Seedream 4.5 vs Nano Banana Pro
Nano Banana Pro ships 4K + best English text rendering. Seedream 4.5 wins on CJK text, Asian-context generation, and per-image cost.
Seedream 4.5 vs Flux 1.1
Flux 1.1 has stronger generic Western aesthetics. Seedream 4.5 dominates on CJK text and structured layouts (posters, infographics with text).
Seedream 4.5 API — Frequently asked questions
Pricing, license, integration — common questions about running Seedream 4.5 on WaveSpeedAI.
What is the Seedream 4.5 API?
Seedream 4.5 is a ByteDance image generation model exposed as a REST API on WaveSpeedAI. ByteDance Seedream 4.5 — fast, affordable image generation and editing with best-in-class CJK text rendering and strong instruction adherence on complex prompts. You can call it programmatically or try it from the playground linked above.
How do I call the Seedream 4.5 API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to "completed", then read the output URL from data.outputs[0]. Full Python / Node.js / cURL examples are above.
How much does the Seedream 4.5 API cost?
Seedream 4.5 starts at $0.040 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Seedream 4.5 variants are available?
WaveSpeedAI hosts 4 Seedream 4.5 endpoints: bytedance/seedream-v4.5/sequential, bytedance/seedream-v4.5, bytedance/seedream-v4.5/edit-sequential, bytedance/seedream-v4.5/edit. Each variant has its own playground page and pricing.
Can I use Seedream 4.5 outputs commercially?
Commercial usage rights follow the ByteDance model license. Most ByteDance models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Seedream 4.5 on WaveSpeedAI instead of going direct?
One API key + one billing account across Seedream 4.5 AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below ByteDance's direct API.
About ByteDance
The team behind Seedream 4.5 and the broader ByteDance model lineup on WaveSpeedAI.
ByteDance — the company behind TikTok, CapCut, and Doubao — runs one of the largest AI research operations in the world. Its Seed and Doubao teams ship state-of-the-art models for video generation (Seedance), image generation and editing (Seedream, Nano Banana), and avatar / lip-sync work. Models are trained on internal-scale data and shipped to production through ByteDance's consumer apps before being released as APIs.
Start building with Seedream 4.5 on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from ByteDance and every other provider.



