Qwen Image 2.1 Image To Image
Qwen Image 2.1 image-to-image mode supports up to 10 reference images for multi-image editing and style transfer. Native 2K resolution output with 40-step inference and 7 aspect ratio options.
Key Features
- Up to 10 reference images — provide multiple reference images for style transfer, composition guidance, or multi-subject editing.
- Native 2K resolution — all outputs are generated at 2K-class dimensions without upscaling.
- 40-step inference — high-quality editing that preserves reference image characteristics.
- 7 aspect ratio options — 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16.
- Multi-image composition — combine elements from multiple reference images in a single generation.
- RGBA output — native transparency support for compositing workflows.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Description of the image to generate or the edit to apply to the reference images. |
| image | Yes | One or more reference image URLs (up to 10). Guides the generation style, composition, or content. |
| aspect_ratio | No | Aspect ratio: 1:1 (default), 4:3, 3:4, 3:2, 2:3, 16:9, 9:16. |
How to Use
- Upload one or more reference images (up to 10) to guide the generation.
- Describe what you want in the prompt — reference the uploaded images for style, composition, or content guidance.
- Select an aspect ratio from the 7 available options.
- Use multiple reference images for complex multi-subject compositions or style blending.
Code Examples
import os
import requests
response = requests.post(
"https://aircube.ai/api/v3/qwen-image-2.1/image-to-image",
headers={
"Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
"Content-Type": "application/json",
},
json={
"prompt": "Apply the artistic style of the reference image to create a landscape with mountains and a river",
"image": "https://example.com/style-reference.jpg",
"aspect_ratio": "16:9"
},
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 | $0.03 |
Billing rules
- Per image: 2k: $0.03.
- Failed generations are not charged.
Best Use Cases
- Style transfer — apply the style of reference images to new compositions at 2K resolution.
- Multi-reference composition — combine elements from up to 10 images into a cohesive output.
- Product photo editing — enhance or restyle product images while preserving key details.
- Character consistency — maintain character identity across multiple generations using reference images.
- Scene reconstruction — recreate scenes from multiple angle references.
- Design iteration — rapidly explore variations using existing images as references.
Pro Tips
- Use more reference images for better style and content consistency.
- Be specific in your prompt about how to use the reference images — e.g., 'use the style from image 1 and the pose from image 2'.
- The model handles up to 10 reference images — use them for complex multi-subject scenes.
- All outputs are 2K resolution — ideal for production-quality edits.
- Combine with text-to-image mode first to generate a base, then refine with image-to-image.
Notes
- Supports 1–10 reference images per generation.
- Fixed 2K output resolution across all aspect ratios.
- Same pricing as text-to-image mode.


