Image Size isteğe bağlı
The size of the generated image.
Square hd Square Portrait 4 3 Portrait 16 9 Landscape 4 3 Landscape 16 9
Num Inference Steps isteğe bağlı
The number of inference steps to perform.
Seed isteğe bağlı
The same seed and the same prompt given to the same version of the model
will output the same image every time.
Loras isteğe bağlı
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 isteğe bağlı
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 isteğe bağlı
The controlnets to use for the image generation. Only one controlnet is supported at the moment.
Controlnet Unions isteğe bağlı
The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.
Ip Adapters isteğe bağlı
IP-Adapter to use for image generation.
Easycontrols isteğe bağlı
EasyControl Inputs to use for image generation.
Fill image isteğe bağlı
Use an image input to influence the generation. Can be used to fill images in masked areas.
Guidance scale isteğe bağlı
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.
Real CFG scale isteğe bağlı
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.
0 1 2 3 4 5
Use Real CFG isteğe bağlı
Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.
If using XLabs IP-Adapter v1, this will be turned on!.
Kapalı Use Real CFG Use CFG-Zero-Init isteğe bağlı
Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.
Kapalı Use CFG-Zero-Init Num Images isteğe bağlı
The number of images to generate. This is always set to 1 for streaming output.
1 2 3 4 5 6 7 8 9 10
Enable Safety Checker isteğe bağlı
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.
Açık Enable Safety Checker Reference Image Url isteğe bağlı
URL of Image for Reference-Only
Reference Strength isteğe bağlı
Strength of reference_only generation. Only used if a reference image is provided.
-3 -2 -1 0 1 2 3
Reference Start isteğe bağlı
The percentage of the total timesteps when the reference guidance is to bestarted.
0 1
Reference End isteğe bağlı
The percentage of the total timesteps when the reference guidance is to be ended.
0 1
Base Shift isteğe bağlı
Base shift for the scheduled timesteps
0.01 1.01 2.01 3.01 4.01
Max Shift isteğe bağlı
Max shift for the scheduled timesteps
0.01 1.01 2.01 3.01 4.01
Output Format isteğe bağlı
The format of the generated image.
Jpeg Png
Use Beta Schedule isteğe bağlı
Specifies whether beta sigmas ought to be used.
Kapalı Use Beta Schedule Sigma Schedule isteğe bağlı
Sigmas schedule for the denoising process.
Scheduler isteğe bağlı
Scheduler for the denoising process.
Euler Dpmpp 2m
Negative Prompt isteğe bağlı
Negative prompt to steer the image generation away from unwanted features.
By default, we will be using NAG for processing the negative prompt.
NAG scale isteğe bağlı
The scale for NAG. Higher values will result in a image that is more distant
to the negative prompt.
NAG Tau isteğe bağlı
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 isteğe bağlı
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 isteğe bağlı
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.
Strength isteğe bağlı
The strength to use for differential diffusion. 1.0 is completely remakes the image while 0.0 preserves the original.
0.01
