You're looking at a specific version of this model. Jump to the model overview.
smkrv /qwen-image:29284901
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
|
Text prompt for image generation
|
|
| negative_prompt |
string
|
|
Negative prompt to guide what not to generate
|
| aspect_ratio |
None
|
1:1
|
Aspect ratio for the generated image
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 100 |
Number of denoising steps. More steps usually give better quality but slower generation
|
| guidance |
number
|
4
Min: 1 Max: 10 |
Guidance scale for generation. Higher values follow the prompt more closely
|
| seed |
integer
|
-1
Min: -1 |
Random seed. Set to -1 to randomize
|
| num_outputs |
integer
|
1
Min: 1 Max: 2 |
Number of images to generate
|
| lora_weights |
string
|
|
URL or path to LoRA weights file (safetensors format)
|
| lora_scale |
number
|
1
Max: 2 |
Scale for the main LoRA weights
|
| extra_lora_weights |
string
|
|
URL or path to additional LoRA weights file (safetensors format)
|
| extra_lora_scale |
number
|
1
Max: 2 |
Scale for the extra LoRA weights
|
| output_format |
None
|
webp
|
Output image format
|
| output_quality |
integer
|
95
Min: 80 Max: 100 |
Quality for jpg/webp outputs (higher is better quality)
|
| go_fast |
boolean
|
False
|
Enable fast generation mode using Lightning LoRA (8 steps, ~6x faster). Automatically uses 8 inference steps and cfg_scale=1.0 for optimal speed and quality.
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images
|
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'}