TRStart creating
Menu

FLUX.1 [dev] with Controlnets and Loras

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.

Input

Fields marked * are required. Review the price before generating.

The prompt to edit the image with

The size of the generated image.

The number of images to generate. This is always set to 1 for streaming output.

URL of Image for Reference-Only

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

URL of image to be edited

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Additional settings

The number of inference steps to perform.

The same seed and the same prompt given to the same version of the model will output the same image every time.

The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.

Tips and requirements

The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs and they will be merged together to generate the final image.

The controlnets to use for the image generation. Only one controlnet is supported at the moment.

The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.

EasyControl Inputs to use for image generation.

Use an image input to influence the generation. Can be used to fill images in masked areas.

URLs of images to be filled for redux prompting

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Tips and requirements

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.

Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.

Strength of reference_only generation. Only used if a reference image is provided.

The percentage of the total timesteps when the reference guidance is to bestarted.

The percentage of the total timesteps when the reference guidance is to be ended.

Base shift for the scheduled timesteps

Max shift for the scheduled timesteps

The format of the generated image.

Specifies whether beta sigmas ought to be used.

Sigmas schedule for the denoising process.

Scheduler for the denoising process.

Tips and requirements

Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt.

The scale for NAG. Higher values will result in a image that is more distant to the negative prompt.

Tips and requirements

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.

Tips and requirements

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 where lower values will result in considering the positive prompt guidance more.

Tips and requirements

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.

The controller guidance (gamma) used in the creation of structured noise.

The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input.

Timestep to start guidance during reverse process.

Timestep to stop guidance during reverse process.

Scheduler for applying reverse guidance.

Price$0.60 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use FLUX.1 [dev] with Controlnets and Loras

Getting started

Try a targeted appearance change while assessing how closely the result follows the source.

Review your result

Compare facial identity, object placement and background detail against the input.

Inputs and settings

Provide image_url and prompt. Keep the initial comparison free of extra loras or controlnets.

controller_guidance_reverse values closer to one favor resemblance to the input. Adjust that setting independently and retain seed before adding further controls.

We use analytics cookies. Privacy policy