You're looking at a specific version of this model. Jump to the model overview.
neurowelt /keros-diffusion:6ce4619b
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
|
Input prompt
|
| richness |
number
|
1.3
Min: 1 Max: 3 |
Low richness gives less detail and a misty look. High values make images stronger, rich, complex. Bugs expected for higher values
|
| contrast |
number
|
1
Min: 0.9 Max: 1.1 |
Quite delicate, can correct overexposure that guidance or richness create. Use 1.0 for no change.
|
| texture |
number
|
1
Min: 0.7 Max: 1.3 |
Low values give high local contrast and sharper changes between objects better for illustrations, glitchcore etc. High values give smooth textures, better for photos.
|
| background |
number
|
0.25
Min: 0.25 Max: 0.3 |
For historical reasons, 0.3 is a starting point equivalent to normal SDXL. 0.25 will (depending on prompt) cancel background objects if they shouldn't be there, allows for single color images or high contrast pure white and black.
|
| focus |
number
|
0
Max: 0.5 |
0.5 will have crispy sharp and contrasty images. 0.25 will be misty and delicate. Scaling is still non-linear, so 0.5 and 0.49 will have high difference compared 0.1 and 0.01 smaller. It's best to keep it as is.
|
| variance |
number
|
0.1
Min: -0.1 Max: 0.1 |
Hardest to control as it changes how other parameters operate. Low value of -0.1 is great for txt2img as it helps to get more interesting results and should be used with high **Richness** (`param1` of 1.0 up to ~2.5). 0.1 is great for img2img as it keeps structure of image but allows large changes in texture and style, to be used with **Richness** of 0.4 up to 1.0.
|
| negative_prompt |
string
|
|
Input Negative Prompt
|
| image |
string
|
Input image for img2img or inpaint mode
|
|
| mask |
string
|
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
|
|
| width |
integer
|
1024
|
Width of output image
|
| height |
integer
|
1024
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| scheduler |
string
(enum)
|
Keros Euler
Options: Keros Euler |
scheduler
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
9
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| refine |
string
(enum)
|
no_refiner
Options: no_refiner, expert_ensemble_refiner, base_image_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, defaults to num_inference_steps
|
|
| apply_watermark |
boolean
|
True
|
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
|
| lora_scale |
number
|
0.6
Max: 1 |
LoRA additive scale. Only applicable on trained models.
|
| disable_safety_checker |
boolean
|
True
|
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
|
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'}