ByteDance Seedream 4.5
doubao/seedream-4.5/text-to-image
ByteDance 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.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | The positive prompt for the generation. |
| sizeSize | select | 2K | 2K | 4K | Output resolution tier. The selected aspect ratio is converted to MaaS pixel dimensions. |
| aspect_ratioAspect Ratio | select | 1:1 | 1:1 | 3:2 | 2:3 | 3:4 | 4:3 | 9:16 | 16:9 | 21:9 | The aspect ratio of the generated image. |
Output fields
| Field | Type | Description |
|---|---|---|
| images | array<string> | Generated image URLs |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/text-to-image" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A futuristic cityscape with towering skyscrapers, neon lights reflecting on wet streets, and flying cars zooming through the sky.",
"size": "4K",
"aspect_ratio": "16:9"
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/text-to-image",
headers=HEADERS,
json={
"input": {
"prompt": "A futuristic cityscape with towering skyscrapers, neon lights reflecting on wet streets, and flying cars zooming through the sky.",
"size": "4K",
"aspect_ratio": "16:9"
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.5/text-to-image", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "A futuristic cityscape with towering skyscrapers, neon lights reflecting on wet streets, and flying cars zooming through the sky.",
"size": "4K",
"aspect_ratio": "16:9"
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
Seedream 4.5
Next-gen text-to-image model optimized for typography and high-resolution outputs
Seedream 4.5 is a state-of-the-art text-to-image model designed for creating visually stunning and text-rich images. With enhanced typography capabilities, strong prompt adherence, and support for resolutions up to 4K, it is ideal for posters, brand visuals, and marketing assets. The model offers ready-to-use REST API integration, ensuring fast performance with no cold starts and competitive pricing.
🚀 Key Features
- Enhanced Typography: Delivers sharp, legible text rendering for posters, logos, and UI designs.
- High-Resolution Output: Supports custom dimensions with resolutions ranging from 512×512 to 8192×8192 pixels.
- Strong Prompt Adherence: Accurately follows detailed descriptions for layout, style, and subject.
- Designer-Level Composition: Handles complex layouts with clear hierarchy, including titles, subtitles, and embedded text.
- Aesthetic Quality: Benchmarked for superior visual quality using industry-standard evaluation tools.
- No Cold Starts: Immediate inference availability ensures consistent and fast performance.
🛠️ Technical Specifications
| Parameter | Description | Default | Range |
|---|---|---|---|
| Prompt | Positive prompt for generation. | - | - |
| Size | Specify width and height of the generated image (pixels). | 2048×2048 | 512×512 to 8192×8192 |
| Resolution | Maximum supported resolution for outputs. | - | Up to 8192×8192 |
| Output Format | URL or BASE64-encoded image. | URL | - |
| Latency | Fast inference without cold starts. | - | - |
Sample Prompts
- Prompt: “A modern poster design with bold typography, featuring a white all-caps title at the top and a small gray subtitle below. Background is abstract with blue gradients.”
- Prompt: “A brand logo with sharp text, minimalist style, and a circular emblem in the center.”
💰 Pricing
| Resolution | Price per Image |
|---|---|
| Standard | $0.04 |
💡 Best Use Cases
- Poster and Banner Design: Create text-heavy visuals for marketing campaigns and events.
- Brand Visual Creation: Generate logos, campaign assets, and branded imagery.
- E-commerce Product Imagery: Produce high-quality hero shots and product visuals.
- Social Media Graphics: Design engaging posts with integrated typography.
🔗 Related Models
- Seedream V4: Previous generation with strong illustration capabilities and diverse styles.
- Nano Banana Pro: Ideal for ultra-low-cost, multi-image generation in large batches.
- Z-Image-Turbo: Optimized for speed and throughput with bilingual support.
- FLUX.2 [Pro]: Best for cinematic, style-flexible hero shots.
Choose Seedream 4.5 for text-heavy creative projects requiring high-resolution outputs and precise typography.
Related models
z-image-spicy/text-to-image
Generate high-quality images from text with custom dimensions from 256 to 1536 pixels, intelligent prompt rewriting, and seed control for creative design and batch generation.
xAI Grok Imagine Image v2.0 Text to Image
xAI Grok Imagine Image V2.0 Text-to-Image generates high-quality images from text prompts, with configurable aspect ratio, resolution, and quality for creative visuals, social content, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Qwen Image 3.0 Pro Text to Image
Qwen Image 3.0 Pro is a professional-grade text-to-image model with superior quality and advanced prompt understanding. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
ai/prefect-pony-xl
Prefect Pony XL delivers high-quality anime-style image generation for character art and illustrations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
OpenAI GPT Image 2 Text-to-Image
OpenAI's GPT Image 2 Text-to-Image generates high-quality images from natural-language prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
OpenAI GPT Image 2 Edit
OpenAI's GPT Image 2 Edit enables image editing from natural-language instructions with one or more reference images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
OpenAI GPT Image 2.5 Sunburst Text-to-Image
High-fidelity image generation for detailed compositions and demanding production work, with up to 4K output.
OpenAI GPT Image 2.5 Flare Text-to-Image
Fast, balanced image generation from natural-language prompts, with up to 4K output.