usamaehsan/flux-multi-controlnet:538edfba – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

usamaehsan /flux-multi-controlnet:538edfba

Input

prompt

string

Shift + Return to add a new line

A girl in city, 25 years old, cool, futuristic styleA girl in city, 25 years old, cool, futuristic style

The text prompt that guides image generation. Be detailed and specific about the image you want to create. Include style, mood, colors, and specific details.

Default: "A girl in city, 25 years old, cool, futuristic style"

canny_image

file

Input image for edge detection control. The Canny ControlNet will use the edges detected in this image to guide the generation. Best for preserving structural elements and outlines.

depth_image

file

Input image for depth control. The Depth ControlNet will preserve the spatial relationships and 3D structure of this image in the generated result. Excellent for maintaining perspective and spatial layout.

lineart_image

file

Input image for line art control. The Lineart ControlNet will follow the artistic lines and sketches in this image. Perfect for turning sketches into detailed artwork while maintaining the original composition.

upscaler_image

file

Input image for upscaling control. The Upscaler ControlNet will enhance and improve the resolution of this image while maintaining its core details and structure. Ideal for improving image quality and adding details.

canny_strength

number

(minimum: 0, maximum: 2)

Controls how strongly the edge detection influences the final image. Higher values (closer to 2.0) follow edge guidance more strictly, lower values (closer to 0) allow more creative freedom.

Default: 0.6

depth_strength

number

(minimum: 0, maximum: 2)

Determines how strictly the depth information influences the generation. Higher values preserve spatial relationships more faithfully, lower values allow more artistic interpretation.

Default: 0.6

lineart_strength

number

(minimum: 0, maximum: 2)

Controls how closely the generated image follows the input line art. Higher values stick closer to the original lines, lower values allow more artistic freedom while maintaining basic composition.

Default: 0.6

upscaler_strength

number

(minimum: 0, maximum: 2)

Determines how much the upscaler influences the final result. Higher values preserve more details from the original image, lower values allow more creative reinterpretation while upscaling.

Default: 0.6

guidance_scale

number

(minimum: 0, maximum: 20)

Controls how closely the image follows the prompt. Higher values (7-20) result in images that more strictly follow the prompt but may be less natural. Lower values (1-7) allow more creative freedom but may stray from the prompt.

Default: 3.5

steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. More steps generally result in higher quality images but take longer to generate. 8-15 steps for quick results, 20-50 for higher quality. Diminishing returns after 30 steps.

Default: 8

seed

integer

Random seed for reproducible results. Using the same seed with identical parameters will generate the same image. Leave as None for random results.

hyperflex_lora_weight

number

(minimum: 0, maximum: 1)

Weight of the HyperFlex LoRA adaptation. Higher values enhance the model's flexibility in interpreting prompts. Recommended range 0.1-0.3 for balanced results.

Default: 0.125

add_details_lora_weight

number

(minimum: 0, maximum: 1)

Weight of the Add Details LoRA adaptation. Higher values enhance fine details and textures in the generated image. Recommended range 0.2-0.5 for enhanced detail.

Default: 0

realism_lora_weight

number

(minimum: 0, maximum: 1)

Weight of the Realism LoRA adaptation. Higher values enhance photorealistic qualities in the generated image. Recommended range 0.3-0.7 for balanced realism.

Default: 0

Including widthh and 1 more...

Run this model in Node.js with one line of code:

npx create-replicate --model=usamaehsan/flux-multi-controlnet

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run usamaehsan/flux-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/flux-multi-controlnet:538edfba331421692f6ba04c32311cad3a6a1fce18fffe51b7393a78064d69b2",
  {
    input: {
      steps: 8,
      prompt: "A girl in city, 25 years old, cool, futuristic style",
      widthh: 0,
      heightt: 0,
      canny_strength: 0.6,
      depth_strength: 0.6,
      guidance_scale: 3.5,
      lineart_strength: 0.6,
      upscaler_strength: 0.6,
      realism_lora_weight: 0,
      hyperflex_lora_weight: 0.125,
      add_details_lora_weight: 0
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run usamaehsan/flux-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/flux-multi-controlnet:538edfba331421692f6ba04c32311cad3a6a1fce18fffe51b7393a78064d69b2",
    input={
        "steps": 8,
        "prompt": "A girl in city, 25 years old, cool, futuristic style",
        "widthh": 0,
        "heightt": 0,
        "canny_strength": 0.6,
        "depth_strength": 0.6,
        "guidance_scale": 3.5,
        "lineart_strength": 0.6,
        "upscaler_strength": 0.6,
        "realism_lora_weight": 0,
        "hyperflex_lora_weight": 0.125,
        "add_details_lora_weight": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run usamaehsan/flux-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "538edfba331421692f6ba04c32311cad3a6a1fce18fffe51b7393a78064d69b2",
    "input": {
      "steps": 8,
      "prompt": "A girl in city, 25 years old, cool, futuristic style",
      "widthh": 0,
      "heightt": 0,
      "canny_strength": 0.6,
      "depth_strength": 0.6,
      "guidance_scale": 3.5,
      "lineart_strength": 0.6,
      "upscaler_strength": 0.6,
      "realism_lora_weight": 0,
      "hyperflex_lora_weight": 0.125,
      "add_details_lora_weight": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.