GET

/v1/schemas/fal/image/fal-ai%2Fflux-general%2Frf-inversion

kind inputactivity imagehash b3d7ee79extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

36 properties · 2 required · 8 $defs
propertytypedescriptionconstraints
prompt*stringThe prompt to edit the image with
image_url*stringURL of image to be edited
reverse_guidance_endintegerTimestep to stop guidance during reverse process.default: 8
use_beta_schedulebooleanSpecifies whether beta sigmas ought to be used.default: false
controlnetsControlNet[]The controlnets to use for the image generation. Only one controlnet is supported at the moment.default: []
image_sizeImageSize | enumThe size of the generated image.
reverse_guidance_startintegerTimestep to start guidance during reverse process.default: 0
lorasLoraWeight[]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.default: []
use_cfg_zerobooleanUses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.default: false
reference_startnumberThe percentage of the total timesteps when the reference guidance is to bestarted.0 ≤ n ≤ 1 · default: 0
nag_endnumberThe 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.0 < n ≤ 1 · default: 0.25
controller_guidance_forwardnumberThe controller guidance (gamma) used in the creation of structured noise.0.01 ≤ n ≤ 3 · default: 0.6
fill_imageImageFillInputUse an image input to influence the generation. Can be used to fill images in masked areas.nullable
max_shiftnumberMax shift for the scheduled timesteps0.01 ≤ n ≤ 5 · default: 1.15
reverse_guidance_scheduleenumScheduler for applying reverse guidance.constant | linear_increase | linear_decrease · default: "constant"
num_imagesintegerThe number of images to generate. This is always set to 1 for streaming output.1 ≤ n ≤ 10 · default: 1
base_shiftnumberBase shift for the scheduled timesteps0.01 ≤ n ≤ 5 · default: 0.5
guidance_scalenumberThe 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.0 ≤ n ≤ 20 · default: 3.5
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.default: true
nag_taunumberThe 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.n > 0 · default: 2.5
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.default: false
reference_strengthnumberStrength of reference_only generation. Only used if a reference image is provided.-3 ≤ n ≤ 3 · default: 0.65
controlnet_unionsControlNetUnion[]The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.default: []
reference_endnumberThe percentage of the total timesteps when the reference guidance is to be ended.0 ≤ n ≤ 1 · default: 1
nag_scalenumberThe scale for NAG. Higher values will result in a image that is more distant to the negative prompt.1 < n ≤ 10 · default: 3
reference_image_urlstringURL of Image for Reference-Only
output_formatenumThe format of the generated image.jpeg | png · default: "png"
nag_alphanumberThe 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 lo…0 < n ≤ 1 · default: 0.25
control_lorasControlLoraWeight[]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.default: []
num_inference_stepsintegerThe number of inference steps to perform.1 ≤ n ≤ 50 · default: 28
easycontrolsEasyControlWeight[]EasyControl Inputs to use for image generation.default: []
negative_promptstringNegative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt.default: ""
seedinteger The same seed and the same prompt given to the same version of the model will output the same image every time. nullable
controller_guidance_reversenumberThe controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input.0.01 ≤ n ≤ 3 · default: 0.75
sigma_scheduleconstSigmas schedule for the denoising process."sgm_uniform" · nullable
schedulerenumScheduler for the denoising process.euler | dpmpp_2m · default: "euler"

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/flux-general/rf-inversion","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}