tgohblio/instant-id-albedobase-xl:2a2afbff | Run with an API on Replicate

Version

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

tgohblio /instant-id-albedobase-xl:2a2afbff

Playground API

Input

image

*file

Input image

prompt

string

Shift + Return to add a new line

cinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeouscinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeous

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"

negative_prompt

string

Shift + Return to add a new line

amateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signatureamateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signature

Input Negative Prompt

Default: ""

width

integer

(minimum: 512, maximum: 2048)

Width of output image

Default: 640

height

integer

(minimum: 512, maximum: 2048)

Height of output image

Default: 640

ip_adapter_scale

number

(minimum: 0, maximum: 1)

Scale for IP adapter

Default: 0.8

controlnet_conditioning_scale

number

(minimum: 0, maximum: 1)

Scale for ControlNet conditioning

Default: 0.8

num_inference_steps

integer

(minimum: 1, maximum: 30)

Number of denoising steps. With LCM-LoRA, optimum is 6-8.

Default: 6

guidance_scale

number

(minimum: 0, maximum: 10)

Scale for classifier-free guidance. With LCM-LoRA, optimum is 0-5.

Default: 0

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=tgohblio/instant-id-albedobase-xl

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

const output = await replicate.run(
  "tgohblio/instant-id-albedobase-xl:2a2afbff09996b53247b0714577d4ff82d2c9da8e8b00c5499b5b34510bb8b5e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KJN1iUhfotriSgNyb05O0NETt8dJR6TGm3utYLYzHSShHAVA/george-michael.jpg",
      width: 768,
      height: 1024,
      prompt: "cinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeous",
      guidance_scale: 0,
      safety_checker: true,
      negative_prompt: "amateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signature",
      ip_adapter_scale: 0.7,
      num_inference_steps: 6,
      controlnet_conditioning_scale: 0.7
    }
  }
);

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

output = replicate.run(
    "tgohblio/instant-id-albedobase-xl:2a2afbff09996b53247b0714577d4ff82d2c9da8e8b00c5499b5b34510bb8b5e",
    input={
        "image": "https://replicate.delivery/pbxt/KJN1iUhfotriSgNyb05O0NETt8dJR6TGm3utYLYzHSShHAVA/george-michael.jpg",
        "width": 768,
        "height": 1024,
        "prompt": "cinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeous",
        "guidance_scale": 0,
        "safety_checker": True,
        "negative_prompt": "amateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signature",
        "ip_adapter_scale": 0.7,
        "num_inference_steps": 6,
        "controlnet_conditioning_scale": 0.7
    }
)
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 tgohblio/instant-id-albedobase-xl 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": "tgohblio/instant-id-albedobase-xl:2a2afbff09996b53247b0714577d4ff82d2c9da8e8b00c5499b5b34510bb8b5e",
    "input": {
      "image": "https://replicate.delivery/pbxt/KJN1iUhfotriSgNyb05O0NETt8dJR6TGm3utYLYzHSShHAVA/george-michael.jpg",
      "width": 768,
      "height": 1024,
      "prompt": "cinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeous",
      "guidance_scale": 0,
      "safety_checker": true,
      "negative_prompt": "amateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signature",
      "ip_adapter_scale": 0.7,
      "num_inference_steps": 6,
      "controlnet_conditioning_scale": 0.7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-19T15:38:55.063797Z",
  "created_at": "2024-03-19T15:35:19.610984Z",
  "data_removed": false,
  "error": null,
  "id": "trki3tdbd7dvhlklptcitctj3m",
  "input": {
    "image": "https://replicate.delivery/pbxt/KJN1iUhfotriSgNyb05O0NETt8dJR6TGm3utYLYzHSShHAVA/george-michael.jpg",
    "width": 768,
    "height": 1024,
    "prompt": "cinematic film still of a man as a jazz singer in 1950s New York city at night, highly detailed face, zavy-cnmtc, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, epic, gorgeous",
    "guidance_scale": 0,
    "safety_checker": true,
    "negative_prompt": "amateur quality, blurry, soft, wrong perspective, wrong angle, ugly, dowdy style, grainy, unnatural lips, digital art, illustration, drawing, painting, sketch, CGI, 3D, render, manga, child, childlike, text, signature",
    "ip_adapter_scale": 0.7,
    "num_inference_steps": 6,
    "controlnet_conditioning_scale": 0.7
  },
  "logs": "[!] Resizing output to 768x1024\nset det-size: (768, 1024)\nwarning: det_size is already set in detection model, ignore\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\n  0%|          | 0/6 [00:00<?, ?it/s]\n 17%|█▋        | 1/6 [00:00<00:02,  1.69it/s]\n 33%|███▎      | 2/6 [00:00<00:01,  2.50it/s]\n 50%|█████     | 3/6 [00:01<00:01,  2.96it/s]\n 67%|██████▋   | 4/6 [00:01<00:00,  3.23it/s]\n 83%|████████▎ | 5/6 [00:01<00:00,  3.40it/s]\n100%|██████████| 6/6 [00:01<00:00,  3.52it/s]\n100%|██████████| 6/6 [00:01<00:00,  3.13it/s]",
  "metrics": {
    "predict_time": 16.532756,
    "total_time": 215.452813
  },
  "output": "https://replicate.delivery/pbxt/2fkfTXze0OKXzp3KvwPrNPFjXeZnCXl1bLdBixAY9KS44YHKB/result.jpg",
  "started_at": "2024-03-19T15:38:38.531041Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/trki3tdbd7dvhlklptcitctj3m",
    "cancel": "https://api.replicate.com/v1/predictions/trki3tdbd7dvhlklptcitctj3m/cancel"
  },
  "version": "2a2afbff09996b53247b0714577d4ff82d2c9da8e8b00c5499b5b34510bb8b5e"
}

Generated in

16.5 seconds

Tweak itReport