You're looking at a specific version of this model. Jump to the model overview.
usamaehsan /qwen-image-edit-fastest-2:06c6dc68
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 |
|---|---|---|---|
| image |
array
|
Input image(s). Single image for editing, or 2-4 images for composition
|
|
| prompt |
string
|
Remove the background
|
Text prompt describing the edit or composition
|
| negative_prompt |
string
|
|
Negative prompt (things to avoid)
|
| aspect_ratio |
None
|
match_input_image
|
Output aspect ratio (only used if width and height are 0)
|
| width |
integer
|
0
Max: 2048 |
Output width (0 = use aspect_ratio)
|
| height |
integer
|
0
Max: 2048 |
Output height (0 = use aspect_ratio)
|
| num_inference_steps |
integer
|
Min: 1 Max: 50 |
Number of steps. Using 2 for maximum speed. Can use 2-4
|
| true_cfg_scale |
number
|
1
Min: 1 Max: 20 |
True CFG scale. Recommended: 1.0-2.0
|
| lora_eigen_weight |
number
|
1
Max: 2 |
Weight for eigen-banana LoRA (0 = disabled, only if LOAD_EIGEN_LORA=True)
|
| lora_angles_weight |
number
|
1.25
Max: 2 |
Weight for multiple-angles LoRA (0 = disabled, 1.0 = normal, 1.25 = strong)
|
| num_images_per_prompt |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
| seed |
integer
|
Random seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}