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.
Bezczynny
$0.04za uruchomienie·~25 / $1
PrzykładyZobacz wszystkie
Nighttime outdoor photoshoot: A young man standsinside a public phone booth, holding a blue phonereceiver to his ear. One hand is casually tucked into his pocket, and he strikes a relaxed posture. He wears a white T-shirt with a pattern, loose brown pants, and jacket draped over his arm. The booth's glass reflects city streetlights with a bokeh effect, creating a vintage film style.
Golden hour rooftop gathering, 16:9, 4K. A group of four friends with diverse skin tones sit and stand around a low table on a city rooftop café, laughing and talking, no visible brands or logos. Use the provided reference portraits (if any) to keep their faces, hairstyles and outfits consistent. Warm sunlight from the side, soft rim light on hair and shoulders, blurred city skyline in the background, string lights glowing above. Casual modern outfits with natural wrinkles and fabric texture, realistic skin details, subtle makeup. Cinematic lifestyle photography, shallow depth of field, slight film grain, clean composition, publish-ready campaign image.
Afternoon side light illuminates the camping tent, withthe rough texture of the tent canvas clearly visible. AGerman Shepherd lies inside; its owner squats down to shake hands with it.
Five shimmering goldfish weave through crevicesbetween stones; four are red-and-white, while one issilver-white.By the pond's edge, a golden shadedBritish Shorthair cat watches them intently, counting onblind luck. Watercolor style
High-end perfume bottle on a reflective black glass surface in a dark studio. Transparent glass bottle with a simple rectangular shape, metallic cap, soft golden liquid inside, no logo or text. A focused warm spotlight from above creates a bright highlight on the bottle and a soft reflection on the surface. Background fades into deep black with a subtle gradient, ultra-realistic product photography, 4K, no text.
Powiązane modele
README
Seedream 4.5
Seedream 4.5 is ’s latest high-resolution image generation model, upgraded through large-scale training and architecture refinement. It is especially strong at typography, poster composition, and branded visuals, with clear text rendering and strong prompt adherence.
Model highlights
- Enhanced typography – Renders sharp, legible text for posters, logos, UI, and marketing layouts.
- Designer-level composition – Handles complex poster-style layouts with clear hierarchy (title, subtitle, body text, logos).
- Strong prompt adherence – Closely follows detailed descriptions for subjects, layout, and style.
- High-resolution output – Supports custom width/height with total pixel count from 2560×1440 up to 8192×8192.
- Aesthetic quality – Benchmarked with strong performance on MagicBench and other visual quality suites.
Recommended use cases
- Poster, banner, and KV design with embedded text
- Brand visual, logo, and campaign asset creation
- E-commerce product imagery and hero shots
- Social media graphics where typography is part of the design
- Presentation, landing-page, and in-app visuals
Pricing
- $0.04 per generated image
How to use
-
Enter your prompt Describe the subject, composition, text elements (e.g., title / subtitle / tagline), and overall style.
-
Set
size(width & height) Choose pixel dimensions for your image. The model supports custom sizes as long as the total pixel count is within 2560×1440 ≤ width × height ≤ 8192×8192. -
Run the job Click Run to generate the image, then refine your prompt or size for the next iteration.
Suggested resolutions
Below are example resolutions that work well in practice and stay within the supported pixel range:
| Aspect Ratio | Suggested Resolution (W × H) |
|---|---|
| 1:1 | 2048 × 2048 |
| 4:3 | 2688 × 2016 |
| 3:2 | 2688 × 1792 |
| 16:9 | 2560 × 1440 |
| Square 4K | 8192 × 8192 |
You can freely adjust width and height as long as they respect the total pixel range.
Notes
- For text-heavy posters, slightly higher resolutions (e.g. 2048×2048 or above) give noticeably cleaner typography.
- Keep logos and key text explicitly described (e.g. “white all-caps title at the top, small gray subtitle below”).
- If you are using an image URL, make sure it is publicly accessible so the system can retrieve it.
Model Comparison on WaveSpeedAI
Use Seedream 4.5 together with other models, depending on your priorities:
-
google/nano-banana-pro/text-to-image – Google’s Nano Banana Pro (Gemini 3.0 Pro Image family) is ideal for ultra-low cost, multi-image generation, great for large batches and exploratory runs.
-
Tongyi-MAI/Z-Image-Turbo (available as Z-Image on WaveSpeedAI) – Tongyi-MAI’s 6B, 8-step turbo model focuses on maximum speed and throughput while keeping photorealism and bilingual (EN/ZH) support.
-
wavespeed-ai/flux-2-pro/text-to-image – FLUX.2 [pro] is a flagship, general-purpose model for cinematic quality and complex scenes, great when you need broad stylistic range beyond typography-heavy posters.
-
/seedream-v4 – The previous Seedream generation, strong at high-resolution illustration and diverse styles; Seedream 4.5 builds on it with noticeably better text rendering and layout control for branding work.
Rule of thumb:
- Choose Seedream 4.5 for posters, brand layouts, and any text-heavy creative.
- Choose Nano Banana Pro or Z-Image-Turbo for fast, cheap, large-scale image batches.
- Choose FLUX.2 [pro] for cinematic, style-flexible hero shots.
- Choose Seedream V4 when you want its familiar look or need variety across illustration styles.
Seedream v4.5 API — Quick start
Grab a WaveSpeedAI API key, then call POST 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]. Examples for Seedream v4.5 below.
HTTP example
# Submit the 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 '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("bytedance/seedream-v4.5", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"enable_base64_output": false,
"enable_sync_mode": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedream-v4.5",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "2048*2048",
"enable_base64_output": false,
"enable_sync_mode": false
}
)
print(output["outputs"][0]) # → URL of the generated outputSeedream v4.5 API — Frequently asked questions
What is the Seedream v4.5 API?
Seedream v4.5 is a ByteDance model for image generation, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.
How do I call the Seedream v4.5 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5.
How much does Seedream v4.5 cost per run?
Seedream v4.5 starts at $0.040 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Seedream v4.5 accept?
Key inputs: `prompt`, `size`, `enable_base64_output`, `enable_sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5.
How long does Seedream v4.5 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 14 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Seedream v4.5 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.