← All models
A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.
images
Details
- Accepts
- image
Pricing
- Price
- 0.156 cr / second
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. |
| loras | array | |
| promptrequired | string | The prompt to edit the image with |
| nag_end | number | The proportion of steps to apply NAG. After the specified proportion of steps has been iterated, the remaining steps will use original attention processors in FLUX. |
| nag_tau | number | The tau for NAG. Controls the normalization of the hidden state. Higher values will result in a less aggressive normalization, but may also lead to unexpected changes with respect to the original image. Not recommended to change this value. |
| image_urlrequired | string | URL of image to be edited |
| max_shift | number | Max shift for the scheduled timesteps |
| nag_alpha | number | The alpha value for NAG. This value is used as a final weighting factor for steering the normalized guidance (positive and negative prompts) in the direction of the positive prompt. Higher values will result in less steering on the normalized guidance… |
| nag_scale | number | The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. |
| scheduler | stringenum: euler, dpmpp_2m | Scheduler for the denoising process. |
| 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. |
| base_shift | number | Base shift for the scheduled timesteps |
| fill_image | — | Use an image input to influence the generation. Can be used to fill images in masked areas. |
| image_size | — | The size of the generated image. |
| num_images | integer | The number of images to generate. This is always set to 1 for streaming output. |
| controlnets | array | The controlnets to use for the image generation. Only one controlnet is supported at the moment. |
| easycontrols | array | EasyControl Inputs to use for image generation. |
| use_cfg_zero | boolean | Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886. |
| control_loras | array | |
| output_format | stringenum: jpeg, png | The format of the generated image. |
| reference_end | number | The percentage of the total timesteps when the reference guidance is to be ended. |
| guidance_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| sigma_schedule | — | Sigmas schedule for the denoising process. |
| negative_prompt | string | Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt. |
| reference_start | number | The percentage of the total timesteps when the reference guidance is to bestarted. |
| controlnet_unions | array | The controlnet unions to use for the image generation. Only one controlnet is supported at the moment. |
| use_beta_schedule | boolean | Specifies whether beta sigmas ought to be used. |
| reference_strength | number | Strength of reference_only generation. Only used if a reference image is provided. |
| num_inference_steps | integer | The number of inference steps to perform. |
| reference_image_url | string | URL of Image for Reference-Only |
| reverse_guidance_end | integer | Timestep to stop guidance during reverse process. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. |
| reverse_guidance_start | integer | Timestep to start guidance during reverse process. |
| reverse_guidance_schedule | stringenum: constant, linear_increase, linear_decrease | Scheduler for applying reverse guidance. |
| controller_guidance_forward | number | The controller guidance (gamma) used in the creation of structured noise. |
| controller_guidance_reverse | number | The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input. |
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 image files info. |
| prompt | string | The prompt used for generating the image. |
| timings | object | |
| has_nsfw_concepts | array | Whether the generated images contain NSFW concepts. |