Select the right model for text-to-image and image editing.
Text-to-image
We recommend wan2.7-image-pro, which combines features like text rendering, brand color control, character-consistent multi-image generation, and image editing. It supports a maximum resolution of 4096x4096 for text-to-image and 2048x2048 for image editing. For detailed instructions, see Text-to-image.
When to use z-image-turbo
For image generation only (no editing functionality).
Speed or cost is a priority: 10x faster generation at about one-fifth the cost.
For photorealistic portraits and product photos.
When to use qwen-image-2.0-pro
To use a negative prompt to exclude specific elements from the output.
To generate up to 6 image variants per call (the Wan standard mode supports up to 4).
Image editing
We recommend wan2.7-image-pro. It supports multi-image reference (up to 9 input images), interactive editing with a bounding box, and character-consistent multi-image generation. For detailed instructions, see Image editing - Qwen and Image editing - Wan2.7/2.6/2.5.
When to use qwen-image-2.0-pro
To use a negative prompt during editing, use qwen-image-2.0-pro (the same model ID is used for both generation and editing).
Recommended models
Model | Use cases | Text-to-image | Editing | Max outputs | Max resolution |
| Text rendering, brand colors, character-consistent multi-image generation, multi-image editing | 4 (12 consecutive) | 4096x4096 (text-to-image) / 2048x2048 (editing) | ||
| Same features as the pro version, with faster generation and a lower maximum resolution (2048x2048). | 4 (12 consecutive) | 2048x2048 | ||
| Fast generation, low cost, photorealistic portraits | 1 | 2048x2048 | ||
| Negative prompts, up to 6 image variants | 6 | 2048x2048 | ||
| A faster version of qwen-image-2.0-pro | 6 | 2048x2048 |
All models
Wan
Model ID | Text-to-image | Editing | Max outputs | Max resolution |
| 4 (12 consecutive) | 4096x4096 (text-to-image) / 2048x2048 (editing) | ||
| 4 (12 consecutive) | 2048x2048 | ||
| 4 | 1440x1440 | ||
| 4 | 1440x1440 | ||
| 4 | 1440x1440 | ||
| 4 | 1280x1280 | ||
| 4 | 1440x1440 | ||
| 4 | 1440x1440 | ||
| 4 | 1440x1440 | ||
| 4 | 1440x1440 | ||
Legacy | ||||
Available only in the China (Beijing) region | 1 | 1024x1024 | ||
Qwen Image
Model ID | Text-to-image | Editing | Max outputs | Max resolution |
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 1 | 1664x928 | ||
| 1 | 1664x928 | ||
| 1 | 1664x928 | ||
| 1 | 1664x928 | ||
| 1 | 1664x928 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 6 | 2048x2048 | ||
| 1 | 1024x1024 |
Z-Image
Model ID | Text-to-image | Editing | Max outputs | Max resolution |
| 1 | 2048x2048 |