usamaehsan/instant-id-x-juggernaut | Run with an API on Replicate

usamaehsan / instant-id-x-juggernaut

Cold

Public
94.4K runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portraitThis is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait

Input prompt

Default: "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality"

image

file

Preview

Input image

image2

file

face image2

pose_image

file

pose image

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

width

integer

(minimum: 0, maximum: 2048)

Width for face detection

Default: 640

height

integer

(minimum: 0, maximum: 2048)

Height for face detection

Default: 640

scheduler

string

Choose a scheduler.

Default: "UniPCMultistep"

min_side

integer

(minimum: 0, maximum: 2048)

min resolution // if resize image is on

Default: 1024

max_side

integer

(minimum: 0, maximum: 2048)

min resolution // if resize image is on

Default: 1280

resize_image

boolean

Default: true

get_age

boolean

Default: true

enhance_face_region

boolean

Default: true

use_controlnet_pose

boolean

Default: true

use_gfpgan

boolean

Default: true

ip_adapter_scale

number

(minimum: 0, maximum: 5)

Scale for IP adapter

Default: 0.8

controlnet_conditioning_scale

number

(minimum: 0, maximum: 5)

Scale for ControlNet conditioning

Default: 0.8

pose_controlnet_conditioning_scale

number

(minimum: 0, maximum: 5)

Scale for ControlNet conditioning

Default: 0.8

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 5

micro_detail_lora_weight

number

disabled on 0

Default: 0

lightning_lora_weight

number

disabled on 0 --> i thinkkk

Default: 0

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

npx create-replicate --model=usamaehsan/instant-id-x-juggernaut

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/instant-id-x-juggernaut using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/instant-id-x-juggernaut:a69b948db098683030b614504f7375c374627604637398dc23eb99db11b33962",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KKhSlVNlQj10hguaYY8wbGgdaxvVBMQmm9Lw6a1PXiRrGCwj/53894527.jpg",
      width: 1051,
      height: 1040,
      prompt: "This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait",
      get_age: true,
      max_side: 1280,
      min_side: 1024,
      scheduler: "UniPCMultistep",
      use_gfpgan: true,
      resize_image: true,
      guidance_scale: 3.5,
      negative_prompt: "",
      ip_adapter_scale: 1,
      enhance_face_region: true,
      num_inference_steps: 10,
      use_controlnet_pose: true,
      lightning_lora_weight: 0,
      micro_detail_lora_weight: 0,
      controlnet_conditioning_scale: 0.6,
      pose_controlnet_conditioning_scale: 0.8
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", 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/instant-id-x-juggernaut using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/instant-id-x-juggernaut:a69b948db098683030b614504f7375c374627604637398dc23eb99db11b33962",
    input={
        "image": "https://replicate.delivery/pbxt/KKhSlVNlQj10hguaYY8wbGgdaxvVBMQmm9Lw6a1PXiRrGCwj/53894527.jpg",
        "width": 1051,
        "height": 1040,
        "prompt": "This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait",
        "get_age": True,
        "max_side": 1280,
        "min_side": 1024,
        "scheduler": "UniPCMultistep",
        "use_gfpgan": True,
        "resize_image": True,
        "guidance_scale": 3.5,
        "negative_prompt": "",
        "ip_adapter_scale": 1,
        "enhance_face_region": True,
        "num_inference_steps": 10,
        "use_controlnet_pose": True,
        "lightning_lora_weight": 0,
        "micro_detail_lora_weight": 0,
        "controlnet_conditioning_scale": 0.6,
        "pose_controlnet_conditioning_scale": 0.8
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.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/instant-id-x-juggernaut 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/instant-id-x-juggernaut:a69b948db098683030b614504f7375c374627604637398dc23eb99db11b33962",
    "input": {
      "image": "https://replicate.delivery/pbxt/KKhSlVNlQj10hguaYY8wbGgdaxvVBMQmm9Lw6a1PXiRrGCwj/53894527.jpg",
      "width": 1051,
      "height": 1040,
      "prompt": "This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait",
      "get_age": true,
      "max_side": 1280,
      "min_side": 1024,
      "scheduler": "UniPCMultistep",
      "use_gfpgan": true,
      "resize_image": true,
      "guidance_scale": 3.5,
      "negative_prompt": "",
      "ip_adapter_scale": 1,
      "enhance_face_region": true,
      "num_inference_steps": 10,
      "use_controlnet_pose": true,
      "lightning_lora_weight": 0,
      "micro_detail_lora_weight": 0,
      "controlnet_conditioning_scale": 0.6,
      "pose_controlnet_conditioning_scale": 0.8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-02-02T09:55:24.702603Z",
  "created_at": "2024-02-02T09:52:10.256367Z",
  "data_removed": false,
  "error": null,
  "id": "2pzv4stboj3qydc3dvd5bppe7u",
  "input": {
    "image": "https://replicate.delivery/pbxt/KKhSlVNlQj10hguaYY8wbGgdaxvVBMQmm9Lw6a1PXiRrGCwj/53894527.jpg",
    "width": 1051,
    "height": 1040,
    "prompt": "This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait",
    "max_side": 1280,
    "min_side": 1024,
    "scheduler": "UniPCMultistep",
    "resize_image": true,
    "guidance_scale": 3.5,
    "negative_prompt": "",
    "ip_adapter_scale": 1,
    "enhance_face_region": true,
    "num_inference_steps": 10,
    "micro_detail_lora_weight": 0,
    "controlnet_conditioning_scale": 0.6
  },
  "logs": "[!] Resizing output to 1051x1040\nset det-size: (1051, 1040)\nwarning: det_size is already set in detection model, ignore\nTime taken to resize image-- : -0.03 seconds\n/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/insightface/utils/transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.\nTo use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.\nP = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4\nTime taken to get face info-- : -6.44 seconds\nTime taken to draw kps-- : -0.14 seconds\nTime taken to enhance face region-- : -0.01 seconds\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:02<00:25,  2.80s/it]\n 20%|██        | 2/10 [00:03<00:12,  1.55s/it]\n 30%|███       | 3/10 [00:04<00:08,  1.16s/it]\n 40%|████      | 4/10 [00:04<00:05,  1.04it/s]\n 50%|█████     | 5/10 [00:05<00:04,  1.16it/s]\n 60%|██████    | 6/10 [00:06<00:03,  1.26it/s]\n 70%|███████   | 7/10 [00:06<00:02,  1.32it/s]\n 80%|████████  | 8/10 [00:07<00:01,  1.37it/s]\n 90%|█████████ | 9/10 [00:08<00:00,  1.40it/s]\n100%|██████████| 10/10 [00:08<00:00,  1.43it/s]\n100%|██████████| 10/10 [00:08<00:00,  1.13it/s]\n/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/peft/tuners/lora/layer.py:595: UserWarning: Already unmerged. Nothing to do.\nwarnings.warn(\"Already unmerged. Nothing to do.\")\n/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/peft/tuners/lora/layer.py:256: UserWarning: Already unmerged. Nothing to do.\nwarnings.warn(\"Already unmerged. Nothing to do.\")",
  "metrics": {
    "predict_time": 18.86616,
    "total_time": 194.446236
  },
  "output": "https://replicate.delivery/pbxt/GmXcXWqOpwoFGFfpmqE8Rt2Twh7hx5YgY2MYN7odYt2FcTJJA/result.jpg",
  "started_at": "2024-02-02T09:55:05.836443Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2pzv4stboj3qydc3dvd5bppe7u",
    "cancel": "https://api.replicate.com/v1/predictions/2pzv4stboj3qydc3dvd5bppe7u/cancel"
  },
  "version": "3af6cc3f0b1491a877230dbc31554c6303b786d46f1c0926ff5cd36cdd0f02a2"
}

Generated in

18.9 seconds

Tweak it Report View full prediction

This output was created using a different version of the model, usamaehsan/instant-id-x-juggernaut:3af6cc3f.

Examples

View more examples

Run time and cost

This model costs approximately $2.84 to run on Replicate, or 0 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 49 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.