generate_image
Create images from text prompts, edit existing images with inpainting, or apply artistic styles using the Ideogram V3 Balanced model.
Instructions
Generate an image using Ideogram V3 Balanced model via Replicate API. Supports text-to-image, inpainting, and style transfer.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text prompt for image generation | |
| aspect_ratio | No | Aspect ratio. Ignored if a resolution or inpainting image is given. | 1:1 |
| resolution | No | Resolution. Overrides aspect ratio. Ignored if an inpainting image is given. | None |
| magic_prompt_option | No | Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. | Auto |
| image | No | An image file to use for inpainting. You must also use a mask. | |
| mask | No | A black and white image. Black pixels are inpainted, white pixels are preserved. | |
| style_type | No | The styles help define the specific aesthetic of the image you want to generate. | None |
| style_reference_images | No | A list of images to use as style references. | |
| seed | No | Random seed. Set for reproducible generation | |
| style_preset | No | Apply a predefined artistic style to the generated image (V3 models only). | None |