You're looking at a specific version of this model. Jump to the model overview.
benjyazoulay /z-image-turbo-lora-controlnet:b3506b91
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
|
TOK Henri Rousseau style painting of a woman
|
Text prompt for image generation
|
| num_inference_steps |
integer
|
20
Min: 1 Max: 200 |
Number of inference steps
|
| guidance_scale |
number
|
0
Max: 20 |
Guidance scale
|
| seed |
integer
|
-1
|
Random seed (-1 random)
|
| controlnet_1 |
None
|
canny
|
ControlNet type
|
| controlnet_1_image |
string
|
https://uploads5.wikiart.org/images/amedeo-modigliani/little-serving-woman-1919.jpg
|
URL of the control image
|
| controlnet_1_end |
number
|
1
Max: 1 |
ControlNet strength (0.0-1.0)
|
| lora_weights |
string
|
https://huggingface.co/BenjaminAzoulay/trainings/resolve/main/henri_rousseau_000003000.safetensors
|
URL of LoRA weights (.safetensors or .tar)
|
| lora_scale |
number
|
1
Max: 2 |
Scale for LoRA weights
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
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'}