generate_image
Generate anime images from text prompts using NovelAI's diffusion models with customizable parameters like scale, steps, and negative prompts.
Instructions
Generate high-quality anime images using NovelAI
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text prompt for image generation | |
| model | No | Model to use (default: "nai-diffusion-3") | nai-diffusion-3 |
| sampler | No | Sampler algorithm (default: "k_euler_ancestral") | k_euler_ancestral |
| seed | No | Random seed (default: -1 for random) | |
| negative_prompt | No | Negative prompt to avoid unwanted elements (default: "") | |
| n_samples | No | Number of images to generate (default: 1) | |
| width | No | Image width (default: 512) | |
| height | No | Image height (default: 768) | |
| scale | No | CFG scale - prompt adherence (default: 5.0) | |
| steps | No | Number of generation steps (default: 28) | |
| save_to_file | No | Save image to local file (default: false) | |
| output_dir | No | Output directory for saved images (default: Desktop/novelai_images) | |
| filename | No | Custom filename (without extension, default: auto-generated) | |
| v4_prompt | No | Advanced V4 prompt format for character positioning | |
| dynamic_thresholding | No | Enable dynamic thresholding for better contrast (default: false) | |
| variety_boost | No | Enable variety boost for more diverse results (default: false) | |
| quality_toggle | No | Enable quality toggle (default: false) |