Available now

FLUX.1 RF-Inversion: image editing

By Black Forest Labs

FLUX.1 RF-Inversion edits a photo you upload from a written prompt and keeps the layout of the original.

Model ID
Maker
Black Forest Labs

Input

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

Example prompt. Edit it or write your own.

This is always set to 1 for streaming output.

The Image for Reference-Only

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The image to be edited

Uploading a file needs an account. Create account

JPEG, 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.

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

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

Only one controlnet is supported at the moment.

Only one controlnet is supported at the moment.

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

The images to be filled for redux prompting

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

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

Specifies whether beta sigmas ought to be used.

Sigmas schedule for the denoising process.

Scheduler for the denoising process.

Negative prompt to steer the image generation away from unwanted features.

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

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.

About this model

Overview

Upload an image and write how it should look: a new season, a different style, another outfit. The model works back from your image to its starting noise, then rebuilds it toward the prompt, so the composition of the original stays in place.

Two controller settings decide how far it may move: values near 1 on the reverse side keep the result close to your image. For advanced work you can add LoRAs, ControlNets and a reference image, and request up to 10 images per run.

What you can build

  • Restyled photos: a painting, a sketch or a film look
  • Seasonal or weather versions of the same scene
  • Character edits that keep the pose and framing
  • Branded looks through your own LoRA

Prompting tips

  • Describe the finished image, not the change: "a portrait of a man with a grey beard" works better than "add a beard".
  • If the result drifts too far from your photo, raise the reverse controller guidance toward 1.
  • Keep the image size close to the source shape so the layout carries over cleanly.

What to check

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

Inputs

  • Prompt (required): The prompt to edit the image with.
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 1 to 50.
  • Seed (optional): The same seed and the same prompt given to the same version of the model will output the same image every time.
  • Loras (optional): 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.
  • Control Loras (optional): 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.
  • Controlnets (optional): The controlnets to use for the image generation. Only one controlnet is supported at the moment.
  • Controlnet Unions (optional): The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.
  • Easycontrols (optional): EasyControl Inputs to use for image generation.
  • Image Fill (optional): Use an image input to influence the generation. Can be used to fill images in masked areas.
  • Guidance scale (CFG) (optional): 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. From 0 to 20.
  • Use CFG-Zero-Init (optional)
  • Number of Images (optional): The number of images to generate. This is always set to 1 for streaming output. From 1 to 10.
  • Reference Image (optional): URL of Image for Reference-Only.
  • Reference Strength (optional): Only used if a reference image is provided. From -3 to 3.
  • Reference Start (optional): The percentage of the total timesteps when the reference guidance is to bestarted. From 0 to 1.
  • Reference End (optional): The percentage of the total timesteps when the reference guidance is to be ended. From 0 to 1.
  • Base Shift (optional): Base shift for the scheduled timesteps. From 0.01 to 5.
  • Max Shift (optional): Max shift for the scheduled timesteps. From 0.01 to 5.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Use Beta Schedule (optional): Specifies whether beta sigmas ought to be used.
  • Sigma Schedule (optional): Sigmas schedule for the denoising process.
  • Scheduler (optional): Scheduler for the denoising process. Options: euler, Dpmpp 2m.
  • Negative Prompt (optional): Negative prompt to steer the image generation away from unwanted features.
  • NAG scale (optional): The scale for NAG. Higher values will result in a image that is more distant to the negative prompt.
  • NAG Tau (optional): 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.
  • NAG alpha (optional): 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.
  • Proportion of steps to apply NAG (optional): 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.
  • Image (required): URL of image to be edited.
  • Controller Guidance Forward (optional): The controller guidance (gamma) used in the creation of structured noise. From 0.01 to 3.
  • Controller Guidance Reverse (optional): The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input. From 0.01 to 3.
  • Reverse Guidance Start (optional): Timestep to start guidance during reverse process.
  • Reverse Guidance End (optional): Timestep to stop guidance during reverse process.
  • Reverse Guidance Schedule (optional): Scheduler for applying reverse guidance. Options: constant, Linear increase, Linear decrease.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: JPEG, PNG.
  • Up to 10 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to: $0.60 / run