← All models
Flux Vision Upscaler for magnify/upscaling images with high fidelity and creativity.
Details
- Accepts
- image
Pricing
- Price
- 12.5 cr / megapixel
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | The seed to use for the upscale. If not provided, a random seed will be used. |
| steps | integer | Number of inference steps (4-50). |
| guidance | number | CFG/guidance scale (1-4). Controls how closely the model follows the prompt. |
| image_urlrequired | string | The URL of the image to upscale. |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
| creativity | number | The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling. |
| upscale_factor | number | The upscale factor (1-4x). |
| enable_safety_checker | boolean | Whether to enable the safety checker. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used to generate the image. |
| image | — | The URL of the generated image. |
| caption | string | The VLM-generated caption used for upscaling. |
| timings | object | The timings of the different steps in the workflow. |