You're looking at a specific version of this model. Jump to the model overview.
beenga /beenga-image-1:75c39988
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
|
What to generate, or what to change if you supply an image. "
"Write it plainly — Beenga handles the phrasing.
|
|
| images |
array
|
[]
|
Source images to edit or reference. Leave empty to generate "
"from scratch. With images, the prompt is an instruction — "
"'change the sari to green', 'put her on a rooftop at night'. "
"Pass more than one to hold a subject across a scene. Max 5.
|
| aspect_ratio |
None
|
1:1
|
Output shape. Ignored when editing — the source image's "
"dimensions are kept.
|
| num_inference_steps |
integer
|
4
Min: 1 Max: 50 |
Denoising steps. The distilled model is tuned for 4.
|
| guidance_scale |
number
|
3.5
Max: 10 |
Prompt adherence strength
|
| seed |
integer
|
Fix for reproducible output. Leave blank for random.
|
|
| curl_enhance |
boolean
|
False
|
Sharpen salon-curl geometry using Beenga's curl adapter. "
"Off by default: it also nudges unspecified hair toward curly.
|
| beenga_prompt_layer |
boolean
|
True
|
Apply Beenga's Indian-context prompt adherence. "
"Turn off to see the raw model's behaviour.
|
| output_format |
None
|
png
|
Image format
|
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'}