viktorfa/instant-id-multicontrolnet-multiple-images

viktorfa / instant-id-multicontrolnet-multiple-images

Cold

Public
76 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

face_image_path

*file

Image of your face

face_image_path2

file

Image of your face

face_image_path3

file

Image of your face

face_image_path4

file

Image of your face

pose_image_path

file

Reference pose image

prompt

string

Shift + Return to add a new line

Input prompt

Default: "a person"

negative_prompt

string

Shift + Return to add a new line

(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy

Input negative prompt

Default: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy"

model

string

Select SDXL model

Default: "RealVisXL V4.0"

enable_fast_mode

boolean

Enable SDXL-lightning fast inference. If pose, canny or depth map is used, disable it for better quality images.

Default: false

lightning_steps

string

if enable fast mode, choose number of denoising steps

Default: "4step"

scheduler

string

Scheduler options. If enable fast mode, this is not used.

Default: "DPMSolverMultistepScheduler-Karras-SDE"

adapter_strength_ratio

number

(minimum: 0, maximum: 1)

Image adapter strength (for detail)

Default: 0.8

identitynet_strength_ratio

number

(minimum: 0, maximum: 1)

IdentityNet strength (for fidelity)

Default: 0.9

pose

boolean

Use pose for skeleton inference

Default: false

pose_strength

number

(minimum: 0, maximum: 1.5)

Default: 1

canny

boolean

Use canny for edge detection

Default: false

canny_strength

number

(minimum: 0, maximum: 1.5)

Default: 0.5

depth_map

boolean

Use depth for depth map estimation

Default: false

depth_strength

number

(minimum: 0, maximum: 1.5)

Default: 0.5

num_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. If enable fast mode, this is not used.

Default: 25

guidance_scale

number

(minimum: 0, maximum: 10)

Scale for classifier-free guidance. Optimum is 4-8. If enable fast mode, this is not used.

Default: 7

seed

integer

(minimum: 0, maximum: 2147483647)

Seed number. Set to non-zero to make the image reproducible.

Default: 0

enhance_non_face_region

boolean

Enhance non-face region

Default: true

num_images

integer

(minimum: 1, maximum: 4)

Number of images to generate

Default: 1

safety_checker

boolean

Safety checker is enabled by default. Un-tick to expose unfiltered results.

Default: true

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

npx create-replicate --model=viktorfa/instant-id-multicontrolnet-multiple-images

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";
import fs from "node:fs";

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

Run viktorfa/instant-id-multicontrolnet-multiple-images using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "viktorfa/instant-id-multicontrolnet-multiple-images:375cbfdc44d6f26ca60c4571962c51c7f49b24336d48f477de033e6ecbf460e9",
  {
    input: {
      pose: false,
      seed: 0,
      canny: false,
      model: "RealVisXL V4.0",
      prompt: "a person",
      depth_map: false,
      num_steps: 25,
      scheduler: "DPMSolverMultistepScheduler-Karras-SDE",
      num_images: 1,
      pose_strength: 1,
      canny_strength: 0.5,
      depth_strength: 0.5,
      guidance_scale: 7,
      safety_checker: true,
      lightning_steps: "4step",
      negative_prompt: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy",
      enable_fast_mode: false,
      adapter_strength_ratio: 0.8,
      enhance_non_face_region: true,
      identitynet_strength_ratio: 0.9
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 viktorfa/instant-id-multicontrolnet-multiple-images using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "viktorfa/instant-id-multicontrolnet-multiple-images:375cbfdc44d6f26ca60c4571962c51c7f49b24336d48f477de033e6ecbf460e9",
    input={
        "pose": False,
        "seed": 0,
        "canny": False,
        "model": "RealVisXL V4.0",
        "prompt": "a person",
        "depth_map": False,
        "num_steps": 25,
        "scheduler": "DPMSolverMultistepScheduler-Karras-SDE",
        "num_images": 1,
        "pose_strength": 1,
        "canny_strength": 0.5,
        "depth_strength": 0.5,
        "guidance_scale": 7,
        "safety_checker": True,
        "lightning_steps": "4step",
        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy",
        "enable_fast_mode": False,
        "adapter_strength_ratio": 0.8,
        "enhance_non_face_region": True,
        "identitynet_strength_ratio": 0.9
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 viktorfa/instant-id-multicontrolnet-multiple-images 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": "viktorfa/instant-id-multicontrolnet-multiple-images:375cbfdc44d6f26ca60c4571962c51c7f49b24336d48f477de033e6ecbf460e9",
    "input": {
      "pose": false,
      "seed": 0,
      "canny": false,
      "model": "RealVisXL V4.0",
      "prompt": "a person",
      "depth_map": false,
      "num_steps": 25,
      "scheduler": "DPMSolverMultistepScheduler-Karras-SDE",
      "num_images": 1,
      "pose_strength": 1,
      "canny_strength": 0.5,
      "depth_strength": 0.5,
      "guidance_scale": 7,
      "safety_checker": true,
      "lightning_steps": "4step",
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy",
      "enable_fast_mode": false,
      "adapter_strength_ratio": 0.8,
      "enhance_non_face_region": true,
      "identitynet_strength_ratio": 0.9
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/viktorfa/instant-id-multicontrolnet-multiple-images@sha256:375cbfdc44d6f26ca60c4571962c51c7f49b24336d48f477de033e6ecbf460e9 \
  -i 'pose=false' \
  -i 'seed=0' \
  -i 'canny=false' \
  -i 'model="RealVisXL V4.0"' \
  -i 'prompt="a person"' \
  -i 'depth_map=false' \
  -i 'num_steps=25' \
  -i 'scheduler="DPMSolverMultistepScheduler-Karras-SDE"' \
  -i 'num_images=1' \
  -i 'pose_strength=1' \
  -i 'canny_strength=0.5' \
  -i 'depth_strength=0.5' \
  -i 'guidance_scale=7' \
  -i 'safety_checker=true' \
  -i 'lightning_steps="4step"' \
  -i 'negative_prompt="(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy"' \
  -i 'enable_fast_mode=false' \
  -i 'adapter_strength_ratio=0.8' \
  -i 'enhance_non_face_region=true' \
  -i 'identitynet_strength_ratio=0.9'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/viktorfa/instant-id-multicontrolnet-multiple-images@sha256:375cbfdc44d6f26ca60c4571962c51c7f49b24336d48f477de033e6ecbf460e9
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "pose": false,
      "seed": 0,
      "canny": false,
      "model": "RealVisXL V4.0",
      "prompt": "a person",
      "depth_map": false,
      "num_steps": 25,
      "scheduler": "DPMSolverMultistepScheduler-Karras-SDE",
      "num_images": 1,
      "pose_strength": 1,
      "canny_strength": 0.5,
      "depth_strength": 0.5,
      "guidance_scale": 7,
      "safety_checker": true,
      "lightning_steps": "4step",
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy",
      "enable_fast_mode": false,
      "adapter_strength_ratio": 0.8,
      "enhance_non_face_region": true,
      "identitynet_strength_ratio": 0.9
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

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

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.