← All models
Stepx Edit2
stepx-edit2
Image editby stepx-edit2
Image-to-image editing with Step1X-Edit v2 from StepFun. Reasoning-enhanced modifications through a thinking–editing–reflection loop with MLLM world knowledge for abstract instruction comprehension.
images
Pricing
- Price
- 25 cr / megapixel
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| promptrequired | string | The prompt to generate an image from. |
| image_urlrequired | string | The image URL to generate an image from. Needs to match the dimensions of the mask. |
| 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. |
| output_format | stringenum: jpeg, png | The format of the generated image. |
| guidance_scale | number | The true CFG scale. Controls how closely the model follows the prompt. |
| negative_prompt | string | The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). |
| num_inference_steps | integer | The number of inference steps to perform. Recommended: 50. |
| enable_thinking_mode | boolean | Enable thinking mode. Uses multimodal language model knowledge to interpret abstract editing instructions. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. |
| enable_reflection_mode | boolean | Enable reflection mode. Reviews outputs, corrects unintended changes, and determines when editing is complete. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed. |
| images | array | The generated images |
| prompt | string | The prompt used for generating the image. |
| timings | object | |
| best_info | — | Reflection analysis (only available when reflection mode is enabled). |
| think_info | — | Reasoning process details (only available when thinking mode is enabled). |
| reformat_prompt | — | The model's interpretation of your instruction (only available when thinking mode is enabled). |
| has_nsfw_concepts | array | Whether the generated images contain NSFW concepts. |