usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter

usamaehsan

controlnet-x-majic-mix-realistic-x-ip-adapter

Cold

works with inpainting and multi-controlnet + single-controlnet || ip-adapter + without ip adapter

Public

23.8K runs

L40S

Run with an API

Pricing

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

Prompt - using compel, use +++ to increase words weight:: doc: https://github.com/damian0815/compel/tree/main/doc || https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#attention-weighting

negative_prompt

string

Shift + Return to add a new line

(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,

Negative prompt - using compel, use +++ to increase words weight

Default: "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"

num_inference_steps

integer

Steps to run denoising

Default: 20

guidance_scale

number

(minimum: 0.1, maximum: 30)

Scale for classifier-free guidance

Default: 7

seed

integer

Seed

eta

number

Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise

Default: 0

guess_mode

boolean

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.

Default: false

disable_safety_check

boolean

Disable safety check. Use at your own risk!

Default: false

num_outputs

integer

(minimum: 1, maximum: 10)

Number of images to generate

Default: 1

max_width

integer

Max width/Resolution of image

Default: 512

max_height

integer

Max height/Resolution of image

Default: 512

scheduler

string

Choose a scheduler.

Default: "DDIM"

lineart_image

file

Preview

Control image for canny controlnet

lineart_conditioning_scale

number

Conditioning scale for canny controlnet

Default: 1

scribble_image

file

Control image for scribble controlnet

scribble_conditioning_scale

number

Conditioning scale for scribble controlnet

Default: 1

tile_image

file

Control image for tile controlnet

tile_conditioning_scale

number

Conditioning scale for tile controlnet

Default: 1

brightness_image

file

Control image for brightness controlnet

brightness_conditioning_scale

number

Conditioning scale for brightness controlnet

Default: 1

inpainting_image

file

Control image for inpainting controlnet

mask_image

file

mask image for inpainting controlnet

inpainting_conditioning_scale

number

Conditioning scale for brightness controlnet

Default: 1

sorted_controlnets

string

Shift + Return to add a new line

Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart

Default: "tile, inpainting, lineart"

ip_adapter_ckpt

string

IP Adapter checkpoint

Default: "ip-adapter_sd15.bin"

ip_adapter_image

file

Preview

IP Adapter image

ip_adapter_weight

number

IP Adapter weight

Default: 1

img2img_image

file

Image2image image

img2img_strength

number

img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image

Default: 0.5

add_more_detail_lora_scale

number

Scale/ weight of more_details lora, more scale = more details

Default: 0.5

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

npx create-replicate --model=usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter

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 usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter:0ee845d75ba767bcad9743837b4e9a495f2032459d055b4ceeab4726a0c0489d",
  {
    input: {
      eta: 0,
      prompt: "cat",
      max_width: 712,
      scheduler: "K_EULER_ANCESTRAL",
      guess_mode: false,
      max_height: 712,
      num_outputs: 1,
      lineart_image: "https://replicate.delivery/pbxt/JvfJGnmbU8uxfzsCeqLBCdEoeOQT09xZOAQLGbGLqyNYrrKc/output.png",
      guidance_scale: 8.72,
      ip_adapter_ckpt: "ip-adapter_sd15.bin",
      negative_prompt: "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,",
      img2img_strength: 0.5,
      ip_adapter_image: "https://replicate.delivery/pbxt/JvfJGnjAmUqqNLFm8OyfbOXynAQLvVOtgSrq2cWOWeAb2wZW/Cool-PC-Wallpapers-HD-2.jpg",
      ip_adapter_weight: 0.3,
      sorted_controlnets: "tile, inpainting, lineart",
      num_inference_steps: 30,
      disable_safety_check: true,
      tile_conditioning_scale: 1,
      add_more_detail_lora_scale: 0.5,
      lineart_conditioning_scale: 1.2,
      scribble_conditioning_scale: 1,
      brightness_conditioning_scale: 1,
      inpainting_conditioning_scale: 1
    }
  }
);

// 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 usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter:0ee845d75ba767bcad9743837b4e9a495f2032459d055b4ceeab4726a0c0489d",
    input={
        "eta": 0,
        "prompt": "cat",
        "max_width": 712,
        "scheduler": "K_EULER_ANCESTRAL",
        "guess_mode": False,
        "max_height": 712,
        "num_outputs": 1,
        "lineart_image": "https://replicate.delivery/pbxt/JvfJGnmbU8uxfzsCeqLBCdEoeOQT09xZOAQLGbGLqyNYrrKc/output.png",
        "guidance_scale": 8.72,
        "ip_adapter_ckpt": "ip-adapter_sd15.bin",
        "negative_prompt": "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,",
        "img2img_strength": 0.5,
        "ip_adapter_image": "https://replicate.delivery/pbxt/JvfJGnjAmUqqNLFm8OyfbOXynAQLvVOtgSrq2cWOWeAb2wZW/Cool-PC-Wallpapers-HD-2.jpg",
        "ip_adapter_weight": 0.3,
        "sorted_controlnets": "tile, inpainting, lineart",
        "num_inference_steps": 30,
        "disable_safety_check": True,
        "tile_conditioning_scale": 1,
        "add_more_detail_lora_scale": 0.5,
        "lineart_conditioning_scale": 1.2,
        "scribble_conditioning_scale": 1,
        "brightness_conditioning_scale": 1,
        "inpainting_conditioning_scale": 1
    }
)

# 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 usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter 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": "usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter:0ee845d75ba767bcad9743837b4e9a495f2032459d055b4ceeab4726a0c0489d",
    "input": {
      "eta": 0,
      "prompt": "cat",
      "max_width": 712,
      "scheduler": "K_EULER_ANCESTRAL",
      "guess_mode": false,
      "max_height": 712,
      "num_outputs": 1,
      "lineart_image": "https://replicate.delivery/pbxt/JvfJGnmbU8uxfzsCeqLBCdEoeOQT09xZOAQLGbGLqyNYrrKc/output.png",
      "guidance_scale": 8.72,
      "ip_adapter_ckpt": "ip-adapter_sd15.bin",
      "negative_prompt": "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,",
      "img2img_strength": 0.5,
      "ip_adapter_image": "https://replicate.delivery/pbxt/JvfJGnjAmUqqNLFm8OyfbOXynAQLvVOtgSrq2cWOWeAb2wZW/Cool-PC-Wallpapers-HD-2.jpg",
      "ip_adapter_weight": 0.3,
      "sorted_controlnets": "tile, inpainting, lineart",
      "num_inference_steps": 30,
      "disable_safety_check": true,
      "tile_conditioning_scale": 1,
      "add_more_detail_lora_scale": 0.5,
      "lineart_conditioning_scale": 1.2,
      "scribble_conditioning_scale": 1,
      "brightness_conditioning_scale": 1,
      "inpainting_conditioning_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

seed-31051.png

{
  "completed_at": "2023-11-24T00:30:32.243146Z",
  "created_at": "2023-11-24T00:28:42.830857Z",
  "data_removed": false,
  "error": null,
  "id": "lup6bnlbutbqupmzu5g43fieye",
  "input": {
    "eta": 0,
    "prompt": "cat",
    "max_width": 712,
    "scheduler": "K_EULER_ANCESTRAL",
    "guess_mode": false,
    "max_height": 712,
    "num_outputs": 1,
    "lineart_image": "https://replicate.delivery/pbxt/JvfJGnmbU8uxfzsCeqLBCdEoeOQT09xZOAQLGbGLqyNYrrKc/output.png",
    "guidance_scale": 8.72,
    "negative_prompt": "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,",
    "ip_adapter_image": "https://replicate.delivery/pbxt/JvfJGnjAmUqqNLFm8OyfbOXynAQLvVOtgSrq2cWOWeAb2wZW/Cool-PC-Wallpapers-HD-2.jpg",
    "ip_adapter_weight": 0.3,
    "sorted_controlnets": "tile, inpainting, lineart",
    "num_inference_steps": 30,
    "disable_safety_check": true,
    "tile_conditioning_scale": 1,
    "lineart_conditioning_scale": 1.2,
    "brightness_conditioning_scale": 1,
    "inpainting_conditioning_scale": 1
  },
  "logs": "using ip adapter:: /tmp/tmpca1o91mmCool-PC-Wallpapers-HD-2.jpg\nloading ip adapter\nTime taken to load IP adapter model: 0.01 seconds\nTime taken to load image encoder model: 0.00 seconds\nUsing seed: 31051\nip adapter---\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:06,  4.81it/s]\n 10%|█         | 3/30 [00:00<00:03,  7.73it/s]\n 13%|█▎        | 4/30 [00:00<00:03,  7.75it/s]\n 17%|█▋        | 5/30 [00:00<00:03,  7.76it/s]\n 20%|██        | 6/30 [00:00<00:03,  7.77it/s]\n 23%|██▎       | 7/30 [00:00<00:02,  7.77it/s]\n 27%|██▋       | 8/30 [00:01<00:02,  7.78it/s]\n 30%|███       | 9/30 [00:01<00:02,  7.78it/s]\n 33%|███▎      | 10/30 [00:01<00:02,  7.76it/s]\n 37%|███▋      | 11/30 [00:01<00:02,  7.76it/s]\n 40%|████      | 12/30 [00:01<00:02,  7.76it/s]\n 43%|████▎     | 13/30 [00:01<00:02,  7.75it/s]\n 47%|████▋     | 14/30 [00:01<00:02,  7.75it/s]\n 50%|█████     | 15/30 [00:01<00:01,  7.75it/s]\n 53%|█████▎    | 16/30 [00:02<00:01,  7.76it/s]\n 57%|█████▋    | 17/30 [00:02<00:01,  7.75it/s]\n 60%|██████    | 18/30 [00:02<00:01,  7.75it/s]\n 63%|██████▎   | 19/30 [00:02<00:01,  7.75it/s]\n 67%|██████▋   | 20/30 [00:02<00:01,  7.75it/s]\n 70%|███████   | 21/30 [00:02<00:01,  7.74it/s]\n 73%|███████▎  | 22/30 [00:02<00:01,  7.74it/s]\n 77%|███████▋  | 23/30 [00:02<00:00,  7.74it/s]\n 80%|████████  | 24/30 [00:03<00:00,  7.74it/s]\n 83%|████████▎ | 25/30 [00:03<00:00,  7.74it/s]\n 87%|████████▋ | 26/30 [00:03<00:00,  7.73it/s]\n 90%|█████████ | 27/30 [00:03<00:00,  7.73it/s]\n 93%|█████████▎| 28/30 [00:03<00:00,  7.73it/s]\n 97%|█████████▋| 29/30 [00:03<00:00,  7.73it/s]\n100%|██████████| 30/30 [00:03<00:00,  7.72it/s]\n100%|██████████| 30/30 [00:03<00:00,  7.70it/s]\nsize:  (712, 712)",
  "metrics": {
    "predict_time": 9.723017,
    "total_time": 109.412289
  },
  "output": [
    "https://replicate.delivery/pbxt/VAB6JgQ91AZnIBexOSg1iX6oIMKetsAvOPv4pyWJ6mQnCa7RA/seed-31051.png"
  ],
  "started_at": "2023-11-24T00:30:22.520129Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/lup6bnlbutbqupmzu5g43fieye",
    "cancel": "https://api.replicate.com/v1/predictions/lup6bnlbutbqupmzu5g43fieye/cancel"
  },
  "version": "6871e1d728bb30a0b0490884932674303d7b35ba7e6aa18e668676cccbf9c41f"
}

Generated in

9.7 seconds

Tweak it Iterate in playgroundReport View full prediction

using ip adapter:: /tmp/tmpca1o91mmCool-PC-Wallpapers-HD-2.jpg
loading ip adapter
Time taken to load IP adapter model: 0.01 seconds
Time taken to load image encoder model: 0.00 seconds
Using seed: 31051
ip adapter---
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:06,  4.81it/s]
 10%|█         | 3/30 [00:00<00:03,  7.73it/s]
 13%|█▎        | 4/30 [00:00<00:03,  7.75it/s]
 17%|█▋        | 5/30 [00:00<00:03,  7.76it/s]
 20%|██        | 6/30 [00:00<00:03,  7.77it/s]
 23%|██▎       | 7/30 [00:00<00:02,  7.77it/s]
 27%|██▋       | 8/30 [00:01<00:02,  7.78it/s]
 30%|███       | 9/30 [00:01<00:02,  7.78it/s]
 33%|███▎      | 10/30 [00:01<00:02,  7.76it/s]
 37%|███▋      | 11/30 [00:01<00:02,  7.76it/s]
 40%|████      | 12/30 [00:01<00:02,  7.76it/s]
 43%|████▎     | 13/30 [00:01<00:02,  7.75it/s]
 47%|████▋     | 14/30 [00:01<00:02,  7.75it/s]
 50%|█████     | 15/30 [00:01<00:01,  7.75it/s]
 53%|█████▎    | 16/30 [00:02<00:01,  7.76it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  7.75it/s]
 60%|██████    | 18/30 [00:02<00:01,  7.75it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  7.75it/s]
 67%|██████▋   | 20/30 [00:02<00:01,  7.75it/s]
 70%|███████   | 21/30 [00:02<00:01,  7.74it/s]
 73%|███████▎  | 22/30 [00:02<00:01,  7.74it/s]
 77%|███████▋  | 23/30 [00:02<00:00,  7.74it/s]
 80%|████████  | 24/30 [00:03<00:00,  7.74it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  7.74it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  7.73it/s]
 90%|█████████ | 27/30 [00:03<00:00,  7.73it/s]
 93%|█████████▎| 28/30 [00:03<00:00,  7.73it/s]
 97%|█████████▋| 29/30 [00:03<00:00,  7.73it/s]
100%|██████████| 30/30 [00:03<00:00,  7.72it/s]
100%|██████████| 30/30 [00:03<00:00,  7.70it/s]
size:  (712, 712)

This output was created using a different version of the model, usamaehsan/controlnet-x-majic-mix-realistic-x-ip-adapter:6871e1d7.

Examples

View more examples

Run time and cost

This model costs approximately $0.011 to run on Replicate, or 90 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 12 seconds.

Readme

Follow me on x/Twitter please : https://twitter.com/usamaClick