You're looking at a specific version of this model. Jump to the model overview.
i-tokyo /product-photo-studio:e356f480
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 |
string
|
Input product image (JPG or PNG, single product, max 2048px)
|
|
| background_style |
None
|
white
|
Background style preset. white=white studio | studio=gray seamless | marble=marble surface | wood=wood table | outdoor=outdoor | gradient=pastel gradient
|
| prompt |
string
|
|
Extra prompt appended to the background style preset (optional)
|
| negative_prompt |
string
|
|
Extra negative prompt appended to the built-in negative prompt (optional)
|
| width |
integer
|
1024
Min: 512 Max: 2048 |
Output image width in pixels
|
| height |
integer
|
1024
Min: 512 Max: 2048 |
Output image height in pixels
|
| seed |
integer
|
0
|
Random seed for reproducibility (0 = random each run)
|
| shadow_strength |
number
|
0.5
Max: 1 |
Drop shadow opacity (0.0 = no shadow, 1.0 = strong shadow)
|
| center_object |
boolean
|
True
|
Crop and center the product with padding before inpainting
|
| num_inference_steps |
integer
|
30
Min: 10 Max: 60 |
Number of diffusion steps (more steps = higher quality, slower)
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 20 |
Classifier-free guidance scale (higher = more prompt-adherent)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}