You're looking at a specific version of this model. Jump to the model overview.
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
|
Prompt for generated image
|
|
| enhance_prompt |
boolean
|
False
|
Append a high-detail suffix to the prompt.
|
| lora_weights |
string
|
Load LoRA weights. Supports local .safetensors paths or ZIPs produced by cog train.
|
|
| replicate_weights |
string
|
LoRA ZIP generated by cog train (alternate to lora_weights).
|
|
| lora_scale |
number
|
1
|
Determines how strongly the loaded LoRA should be applied.
|
| image |
string
|
Optional guide image for img2img.
|
|
| strength |
number
|
0.9
Max: 1 |
Strength for img2img pipeline
|
| negative_prompt |
string
|
|
Negative prompt for generated image
|
| aspect_ratio |
None
|
16:9
|
Aspect ratio for the generated image
|
| image_size |
None
|
optimize_for_quality
|
Image size preset (quality = larger, speed = faster).
|
| go_fast |
boolean
|
True
|
Run faster predictions with aggressive caching.
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 50 |
Number of denoising steps (1–50).
|
| guidance |
number
|
3
Max: 10 |
Guidance for generated image (0-10).
|
| seed |
integer
|
Random seed. Leave blank for random.
|
|
| output_format |
None
|
webp
|
Format of the output images
|
| output_quality |
integer
|
80
Max: 100 |
Quality when saving lossy images (0-100).
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker (not used).
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}