You're looking at a specific version of this model. Jump to the model overview.
drawhisper /illustrious-xl:574a982d
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
An astronaut riding a rainbow unicorn
|
Text prompt for image generation
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
| aspect_ratio |
None
|
1:1
|
Aspect ratio for the generated image
|
| output_format |
None
|
webp
|
Output image format
|
| output_quality |
integer
|
80
Max: 100 |
Output image quality (0-100, only for JPEG)
|
| image |
string
|
Input image for image-to-image mode (supports PNG, JPG, WEBP).
|
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
|
| seed |
integer
|
Random seed. Set for reproducible generation
|
|
| go_fast |
boolean
|
False
|
Run faster predictions with reduced quality
|
| guidance |
number
|
7.5
Min: 1 Max: 20 |
Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
|
| megapixels |
None
|
1
|
Approximate number of megapixels for generated image
|
| num_inference_steps |
integer
|
28
Min: 1 Max: 50 |
Number of denoising steps. More steps generally give better quality but take longer
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images
|
| lora_weights |
string
|
Primary LoRA weights. Supports Replicate models (owner/model), HuggingFace (huggingface.co/owner/model), CivitAI (civitai.com/models/id), and direct URLs
|
|
| lora_scale |
number
|
1
Min: -1 Max: 3 |
Primary LoRA scale/strength
|
| extra_lora |
string
|
Secondary LoRA weights. Allows combining two LoRAs simultaneously
|
|
| extra_lora_scale |
number
|
1
Min: -1 Max: 3 |
Secondary LoRA scale/strength
|
| hf_api_token |
string
|
HuggingFace API token for private models
|
|
| civitai_api_token |
string
|
CivitAI API token for private models
|
|
| negative_prompt |
string
|
|
Negative prompt - what you don't want in the image
|
| scheduler |
None
|
K_EULER
|
Sampling scheduler algorithm
|
| cfg_scale |
number
|
7.5
Min: 1 Max: 20 |
Classifier-free guidance scale (same as guidance, kept for SDXL compatibility)
|
| clip_skip |
integer
|
0
Max: 2 |
Number of CLIP layers to skip (advanced parameter)
|
| refine |
None
|
no_refiner
|
Which refine style to use
|
| high_noise_frac |
number
|
0.8
Max: 1 |
For expert_ensemble_refiner, the fraction of noise to use
|
| refine_steps |
integer
|
For base_image_refiner, the number of steps to refine
|
|
| apply_watermark |
boolean
|
False
|
Apply watermark to generated images
|
| use_standard_sdxl |
boolean
|
False
|
Use standard SDXL instead of Illustrious XL (for realistic content)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}