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.
Key Features
- High-fidelity image generation from natural language prompts with photorealistic or stylized outputs.
- Advanced prompt comprehension — accurately interprets complex scenes, spatial relationships and artistic styles.
- Multiple aspect ratio support — generate in landscape, portrait, square or custom dimensions.
- Fine-grained style control through detailed prompt engineering and parameter tuning.
- Fast inference with production-ready API — low latency, no cold starts.
- Consistent quality across diverse subjects: people, landscapes, objects, abstract art and more.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image to generate. |
| aspect_ratio | No | Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4 (default: 1:1). |
| resolution | No | Output resolution tier (default varies by model). |
| seed | No | Seed for reproducible results. |
How to Use
- Open the Playground and write a detailed description of the image you want to create.
- Select your desired aspect ratio and resolution.
- Click Generate and wait for results.
- Download or iterate — refine your prompt for better results.
Code Examples
import os
import requests
response = requests.post(
"https://aircube.ai/api/v3/seedream-v4.5",
headers={
"Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
"Content-Type": "application/json",
},
json={
"prompt": "A serene mountain landscape at sunset, golden light on snow-capped peaks"
},
timeout=300,
)
data = response.json()
if data["success"]:
print("ID:", data["data"]["id"], "Status:", data["data"]["status"])
else:
print("Error:", data["error"]["message"])Pricing
| Resolution | Duration | Cost |
|---|---|---|
| 2k | per image | $0.04 |
| 4k | per image | $0.04 |
Billing rules
- Per image: 2k: $0.04, 4k: $0.04.
- Failed generations are not charged.
Best Use Cases
- Marketing assets — generate hero images, social media visuals and ad creatives.
- Product mockups — quickly visualize product concepts and packaging designs.
- Art and illustration — create custom artwork, book covers and editorial illustrations.
- Storyboarding — generate scene compositions for video and animation planning.
Pro Tips
- Be specific about composition, lighting, and style in your prompts for more predictable results.
- Include art medium keywords (oil painting, watercolor, 3D render, photography) to guide the style.
- Use negative descriptors to avoid unwanted elements — describe what you DO want, not what you don't.
- Start with a lower resolution for fast iterations, then upscale your favorite result.
Notes
- Outputs are saved to your generation history for 7 days.
- Maximum prompt length varies by model — keep prompts under 500 words for best results.
- Content policy applies — harmful or prohibited content will be filtered.