generate_image
Create custom images from text descriptions using AI models. Specify prompts, adjust parameters like size and style, and receive generated image URLs.
Instructions
Generate an image using ModelScope image generation models. The tool will wait until the image is generated and return the image URL.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model to use for image generation. Available options: 'Qwen/Qwen-Image' (default), 'Tongyi-MAI/Z-Image-Turbo' | Qwen/Qwen-Image |
| prompt | Yes | Positive prompt for image generation (English recommended). Max length: 2000 characters | |
| negative_prompt | No | Negative prompt to specify what to avoid in the image. Max length: 2000 characters | |
| size | No | Image resolution size (e.g., '1024x1024'). Range for Qwen-Image: [64x64, 1664x1664]. Default: 1024x1024 | |
| seed | No | Random seed for reproducibility. Range: [0, 2^31-1] | |
| steps | No | Number of sampling steps. Range: [1, 100] | |
| guidance | No | Guidance scale for prompt adherence. Range: [1.5, 20] | |
| image_url | No | URL of the image to edit (only for image editing mode). Must be publicly accessible |