zsxkib / instant-id

image
width: 640
height: 640
prompt: 4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film
sdxl_weights: stable-diffusion-xl-base-1.0
guidance_scale: 5
negative_prompt: ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured
ip_adapter_scale: 0.8
num_inference_steps: 30
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KI4a4NSCc0sAFMdlbD4n8ufHLXb2utKIwwbQff0M2ryhGJPJ/pp_0.jpg",
  "width": 640,
  "height": 640,
  "prompt": "4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film",
  "sdxl_weights": "stable-diffusion-xl-base-1.0",
  "guidance_scale": 5,
  "negative_prompt": "ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
  "ip_adapter_scale": 0.8,
  "num_inference_steps": 30,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:4a86d2bcb78e94f5fcda66492b1acdf8781b252fbe55714fb67b30e66c4512f4",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KI4a4NSCc0sAFMdlbD4n8ufHLXb2utKIwwbQff0M2ryhGJPJ/pp_0.jpg",
      width: 640,
      height: 640,
      prompt: "4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film",
      sdxl_weights: "stable-diffusion-xl-base-1.0",
      guidance_scale: 5,
      negative_prompt: "ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      ip_adapter_scale: 0.8,
      num_inference_steps: 30,
      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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:4a86d2bcb78e94f5fcda66492b1acdf8781b252fbe55714fb67b30e66c4512f4",
    input={
        "image": "https://replicate.delivery/pbxt/KI4a4NSCc0sAFMdlbD4n8ufHLXb2utKIwwbQff0M2ryhGJPJ/pp_0.jpg",
        "width": 640,
        "height": 640,
        "prompt": "4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film",
        "sdxl_weights": "stable-diffusion-xl-base-1.0",
        "guidance_scale": 5,
        "negative_prompt": "ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
        "ip_adapter_scale": 0.8,
        "num_inference_steps": 30,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:4a86d2bcb78e94f5fcda66492b1acdf8781b252fbe55714fb67b30e66c4512f4",
    "input": {
      "image": "https://replicate.delivery/pbxt/KI4a4NSCc0sAFMdlbD4n8ufHLXb2utKIwwbQff0M2ryhGJPJ/pp_0.jpg",
      "width": 640,
      "height": 640,
      "prompt": "4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film",
      "sdxl_weights": "stable-diffusion-xl-base-1.0",
      "guidance_scale": 5,
      "negative_prompt": "ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      "ip_adapter_scale": 0.8,
      "num_inference_steps": 30,
      "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": "2024-01-26T00:14:36.234677Z",
  "created_at": "2024-01-26T00:14:18.514716Z",
  "data_removed": false,
  "error": null,
  "id": "tzqpu7tbuxxeq4u2j7xrpwmymq",
  "input": {
    "image": "https://replicate.delivery/pbxt/KI4a4NSCc0sAFMdlbD4n8ufHLXb2utKIwwbQff0M2ryhGJPJ/pp_0.jpg",
    "width": 640,
    "height": 640,
    "prompt": "4k photo of a man. highly detailed, best quality, shallow depth of field, fuji film",
    "sdxl_weights": "stable-diffusion-xl-base-1.0",
    "guidance_scale": 5,
    "negative_prompt": "ugly, (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
    "ip_adapter_scale": 0.8,
    "num_inference_steps": 30,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:10,  2.79it/s]\n  7%|▋         | 2/30 [00:00<00:09,  2.89it/s]\n 10%|█         | 3/30 [00:01<00:09,  2.92it/s]\n 13%|█▎        | 4/30 [00:01<00:08,  2.94it/s]\n 17%|█▋        | 5/30 [00:01<00:08,  2.95it/s]\n 20%|██        | 6/30 [00:02<00:08,  2.95it/s]\n 23%|██▎       | 7/30 [00:02<00:07,  2.96it/s]\n 27%|██▋       | 8/30 [00:02<00:07,  2.96it/s]\n 30%|███       | 9/30 [00:03<00:07,  2.96it/s]\n 33%|███▎      | 10/30 [00:03<00:06,  2.96it/s]\n 37%|███▋      | 11/30 [00:03<00:06,  2.96it/s]\n 40%|████      | 12/30 [00:04<00:06,  2.95it/s]\n 43%|████▎     | 13/30 [00:04<00:05,  2.96it/s]\n 47%|████▋     | 14/30 [00:04<00:05,  2.96it/s]\n 50%|█████     | 15/30 [00:05<00:05,  2.96it/s]\n 53%|█████▎    | 16/30 [00:05<00:04,  2.96it/s]\n 57%|█████▋    | 17/30 [00:05<00:04,  2.96it/s]\n 60%|██████    | 18/30 [00:06<00:04,  2.95it/s]\n 63%|██████▎   | 19/30 [00:06<00:03,  2.95it/s]\n 67%|██████▋   | 20/30 [00:06<00:03,  2.96it/s]\n 70%|███████   | 21/30 [00:07<00:03,  2.97it/s]\n 73%|███████▎  | 22/30 [00:07<00:02,  2.97it/s]\n 77%|███████▋  | 23/30 [00:07<00:02,  2.97it/s]\n 80%|████████  | 24/30 [00:08<00:02,  2.97it/s]\n 83%|████████▎ | 25/30 [00:08<00:01,  2.97it/s]\n 87%|████████▋ | 26/30 [00:08<00:01,  2.97it/s]\n 90%|█████████ | 27/30 [00:09<00:01,  2.97it/s]\n 93%|█████████▎| 28/30 [00:09<00:00,  2.96it/s]\n 97%|█████████▋| 29/30 [00:09<00:00,  2.96it/s]\n100%|██████████| 30/30 [00:10<00:00,  2.97it/s]\n100%|██████████| 30/30 [00:10<00:00,  2.96it/s]",
  "metrics": {
    "predict_time": 17.633786,
    "total_time": 17.719961
  },
  "output": "https://replicate.delivery/pbxt/Wnbjkn351EbjOBTZi4a8RR0MQ7KJyxSG7K32NefeHbrXbVgkA/result.jpg",
  "started_at": "2024-01-26T00:14:18.600891Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/tzqpu7tbuxxeq4u2j7xrpwmymq",
    "cancel": "https://api.replicate.com/v1/predictions/tzqpu7tbuxxeq4u2j7xrpwmymq/cancel"
  },
  "version": "4a86d2bcb78e94f5fcda66492b1acdf8781b252fbe55714fb67b30e66c4512f4"
}

Generated in

17.6 seconds

Tweak it ShareReport

Prediction

zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e

Model

zsxkib/instant-id:965db266

h3yimr3bw62kvyvup3jg7j6s5y

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

27.1s

Created

over 1 year ago

Input

image
width: 640
height: 640
prompt: minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)
guidance_scale: 5
negative_prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain
ip_adapter_scale: 0.8
num_inference_steps: 30
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KGyS43owe6zh6PpqA2BDoIbPrFy6ef2BOEHvi4nuj5yE2VSq/yann-lecun_resize.jpg",
  "width": 640,
  "height": 640,
  "prompt": "minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)",
  "guidance_scale": 5,
  "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain",
  "ip_adapter_scale": 0.8,
  "num_inference_steps": 30,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KGyS43owe6zh6PpqA2BDoIbPrFy6ef2BOEHvi4nuj5yE2VSq/yann-lecun_resize.jpg",
      width: 640,
      height: 640,
      prompt: "minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)",
      guidance_scale: 5,
      negative_prompt: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain",
      ip_adapter_scale: 0.8,
      num_inference_steps: 30,
      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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
    input={
        "image": "https://replicate.delivery/pbxt/KGyS43owe6zh6PpqA2BDoIbPrFy6ef2BOEHvi4nuj5yE2VSq/yann-lecun_resize.jpg",
        "width": 640,
        "height": 640,
        "prompt": "minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)",
        "guidance_scale": 5,
        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain",
        "ip_adapter_scale": 0.8,
        "num_inference_steps": 30,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
    "input": {
      "image": "https://replicate.delivery/pbxt/KGyS43owe6zh6PpqA2BDoIbPrFy6ef2BOEHvi4nuj5yE2VSq/yann-lecun_resize.jpg",
      "width": 640,
      "height": 640,
      "prompt": "minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)",
      "guidance_scale": 5,
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain",
      "ip_adapter_scale": 0.8,
      "num_inference_steps": 30,
      "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": "2024-01-22T21:56:52.342604Z",
  "created_at": "2024-01-22T21:56:25.196973Z",
  "data_removed": false,
  "error": null,
  "id": "h3yimr3bw62kvyvup3jg7j6s5y",
  "input": {
    "image": "https://replicate.delivery/pbxt/KGyS43owe6zh6PpqA2BDoIbPrFy6ef2BOEHvi4nuj5yE2VSq/yann-lecun_resize.jpg",
    "width": 640,
    "height": 640,
    "prompt": "minimalist, very intricate colours, simplified continuous line colour drawing in the style of ink pen drawing by Michelangelo, white background, colours, heavy use of palette knives, only inky real colours on paper (colours)",
    "guidance_scale": 5,
    "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured, plain",
    "ip_adapter_scale": 0.8,
    "num_inference_steps": 30,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:19,  1.47it/s]\n  7%|▋         | 2/30 [00:01<00:19,  1.47it/s]\n 10%|█         | 3/30 [00:02<00:18,  1.47it/s]\n 13%|█▎        | 4/30 [00:02<00:17,  1.47it/s]\n 17%|█▋        | 5/30 [00:03<00:16,  1.47it/s]\n 20%|██        | 6/30 [00:04<00:16,  1.47it/s]\n 23%|██▎       | 7/30 [00:04<00:15,  1.47it/s]\n 27%|██▋       | 8/30 [00:05<00:14,  1.47it/s]\n 30%|███       | 9/30 [00:06<00:14,  1.47it/s]\n 33%|███▎      | 10/30 [00:06<00:13,  1.47it/s]\n 37%|███▋      | 11/30 [00:07<00:12,  1.47it/s]\n 40%|████      | 12/30 [00:08<00:12,  1.47it/s]\n 43%|████▎     | 13/30 [00:08<00:11,  1.47it/s]\n 47%|████▋     | 14/30 [00:09<00:10,  1.47it/s]\n 50%|█████     | 15/30 [00:10<00:10,  1.47it/s]\n 53%|█████▎    | 16/30 [00:10<00:09,  1.47it/s]\n 57%|█████▋    | 17/30 [00:11<00:08,  1.47it/s]\n 60%|██████    | 18/30 [00:12<00:08,  1.47it/s]\n 63%|██████▎   | 19/30 [00:12<00:07,  1.47it/s]\n 67%|██████▋   | 20/30 [00:13<00:06,  1.47it/s]\n 70%|███████   | 21/30 [00:14<00:06,  1.47it/s]\n 73%|███████▎  | 22/30 [00:14<00:05,  1.46it/s]\n 77%|███████▋  | 23/30 [00:15<00:04,  1.46it/s]\n 80%|████████  | 24/30 [00:16<00:04,  1.46it/s]\n 83%|████████▎ | 25/30 [00:17<00:03,  1.46it/s]\n 87%|████████▋ | 26/30 [00:17<00:02,  1.46it/s]\n 90%|█████████ | 27/30 [00:18<00:02,  1.46it/s]\n 93%|█████████▎| 28/30 [00:19<00:01,  1.46it/s]\n 97%|█████████▋| 29/30 [00:19<00:00,  1.46it/s]\n100%|██████████| 30/30 [00:20<00:00,  1.46it/s]\n100%|██████████| 30/30 [00:20<00:00,  1.47it/s]",
  "metrics": {
    "predict_time": 27.09831,
    "total_time": 27.145631
  },
  "output": "https://replicate.delivery/pbxt/k1c4UVXlTR5aDRMTSUQXQQcCKryKAWhkqMArBU3etQ1RtkHJA/result.jpg",
  "started_at": "2024-01-22T21:56:25.244294Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/h3yimr3bw62kvyvup3jg7j6s5y",
    "cancel": "https://api.replicate.com/v1/predictions/h3yimr3bw62kvyvup3jg7j6s5y/cancel"
  },
  "version": "965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e"
}

Generated in

27.1 seconds

Tweak it ShareReport

Prediction

zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e

Model

zsxkib/instant-id:965db266

vlug6udbjej7rxaci6wi4z77nu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

28.7s

Created

over 1 year ago

Input

image
width: 640
height: 640
prompt: A photo of a scientist img receiving the Nobel Prize
guidance_scale: 5
negative_prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
ip_adapter_scale: 0.8
num_inference_steps: 30
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KGyAY0lYJT1bZezD3QXG7tcDaa99wfrJcxA4BNKi3kUpjPbe/sam_resize.png",
  "width": 640,
  "height": 640,
  "prompt": "A photo of a scientist img receiving the Nobel Prize",
  "guidance_scale": 5,
  "negative_prompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
  "ip_adapter_scale": 0.8,
  "num_inference_steps": 30,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KGyAY0lYJT1bZezD3QXG7tcDaa99wfrJcxA4BNKi3kUpjPbe/sam_resize.png",
      width: 640,
      height: 640,
      prompt: "A photo of a scientist img receiving the Nobel Prize",
      guidance_scale: 5,
      negative_prompt: "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
      ip_adapter_scale: 0.8,
      num_inference_steps: 30,
      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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
    input={
        "image": "https://replicate.delivery/pbxt/KGyAY0lYJT1bZezD3QXG7tcDaa99wfrJcxA4BNKi3kUpjPbe/sam_resize.png",
        "width": 640,
        "height": 640,
        "prompt": "A photo of a scientist img receiving the Nobel Prize",
        "guidance_scale": 5,
        "negative_prompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
        "ip_adapter_scale": 0.8,
        "num_inference_steps": 30,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e",
    "input": {
      "image": "https://replicate.delivery/pbxt/KGyAY0lYJT1bZezD3QXG7tcDaa99wfrJcxA4BNKi3kUpjPbe/sam_resize.png",
      "width": 640,
      "height": 640,
      "prompt": "A photo of a scientist img receiving the Nobel Prize",
      "guidance_scale": 5,
      "negative_prompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
      "ip_adapter_scale": 0.8,
      "num_inference_steps": 30,
      "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": "2024-01-22T22:01:33.655957Z",
  "created_at": "2024-01-22T22:01:04.969963Z",
  "data_removed": false,
  "error": null,
  "id": "vlug6udbjej7rxaci6wi4z77nu",
  "input": {
    "image": "https://replicate.delivery/pbxt/KGyAY0lYJT1bZezD3QXG7tcDaa99wfrJcxA4BNKi3kUpjPbe/sam_resize.png",
    "width": 640,
    "height": 640,
    "prompt": "A photo of a scientist img receiving the Nobel Prize",
    "guidance_scale": 5,
    "negative_prompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
    "ip_adapter_scale": 0.8,
    "num_inference_steps": 30,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:19,  1.47it/s]\n  7%|▋         | 2/30 [00:01<00:19,  1.47it/s]\n 10%|█         | 3/30 [00:02<00:18,  1.47it/s]\n 13%|█▎        | 4/30 [00:02<00:17,  1.47it/s]\n 17%|█▋        | 5/30 [00:03<00:16,  1.47it/s]\n 20%|██        | 6/30 [00:04<00:16,  1.47it/s]\n 23%|██▎       | 7/30 [00:04<00:15,  1.47it/s]\n 27%|██▋       | 8/30 [00:05<00:14,  1.47it/s]\n 30%|███       | 9/30 [00:06<00:14,  1.47it/s]\n 33%|███▎      | 10/30 [00:06<00:13,  1.47it/s]\n 37%|███▋      | 11/30 [00:07<00:12,  1.47it/s]\n 40%|████      | 12/30 [00:08<00:12,  1.47it/s]\n 43%|████▎     | 13/30 [00:08<00:11,  1.47it/s]\n 47%|████▋     | 14/30 [00:09<00:10,  1.47it/s]\n 50%|█████     | 15/30 [00:10<00:10,  1.47it/s]\n 53%|█████▎    | 16/30 [00:10<00:09,  1.47it/s]\n 57%|█████▋    | 17/30 [00:11<00:08,  1.47it/s]\n 60%|██████    | 18/30 [00:12<00:08,  1.47it/s]\n 63%|██████▎   | 19/30 [00:12<00:07,  1.47it/s]\n 67%|██████▋   | 20/30 [00:13<00:06,  1.47it/s]\n 70%|███████   | 21/30 [00:14<00:06,  1.47it/s]\n 73%|███████▎  | 22/30 [00:14<00:05,  1.47it/s]\n 77%|███████▋  | 23/30 [00:15<00:04,  1.47it/s]\n 80%|████████  | 24/30 [00:16<00:04,  1.47it/s]\n 83%|████████▎ | 25/30 [00:17<00:03,  1.47it/s]\n 87%|████████▋ | 26/30 [00:17<00:02,  1.47it/s]\n 90%|█████████ | 27/30 [00:18<00:02,  1.47it/s]\n 93%|█████████▎| 28/30 [00:19<00:01,  1.47it/s]\n 97%|█████████▋| 29/30 [00:19<00:00,  1.47it/s]\n100%|██████████| 30/30 [00:20<00:00,  1.46it/s]\n100%|██████████| 30/30 [00:20<00:00,  1.47it/s]",
  "metrics": {
    "predict_time": 27.176196,
    "total_time": 28.685994
  },
  "output": "https://replicate.delivery/pbxt/m2ssM2QxTr6oPdcvoFnMebtNgDisWXPxIFH9r4fgWOe59SeIB/result.jpg",
  "started_at": "2024-01-22T22:01:06.479761Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/vlug6udbjej7rxaci6wi4z77nu",
    "cancel": "https://api.replicate.com/v1/predictions/vlug6udbjej7rxaci6wi4z77nu/cancel"
  },
  "version": "965db2664428311c75f49036a8ff261e1972ac714efd7d7a1c15c808db021b0e"
}

Generated in

27.2 seconds

Tweak it ShareReport

Prediction

zsxkib/instant-id:6af8583c541261472e92155d87bba80d5ad98461665802f2ba196ac099aaedc9

Model

zsxkib/instant-id:6af8583c

r766fk3ban74fwagxopi7mqsxe

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

47.1s

Created

over 1 year ago

Input

image
width: 640
height: 640
prompt: masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished
scheduler: EulerDiscreteScheduler
enable_lcm
sdxl_weights: nightvision-xl-0791
pose_strength: 0.4
canny_strength: 0.3
depth_strength: 0.5
guidance_scale: 5
negative_prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green
ip_adapter_scale: 0.8
lcm_guidance_scale: 1.5
num_inference_steps: 30
enable_pose_controlnet
enhance_nonface_region
enable_canny_controlnet
enable_depth_controlnet
lcm_num_inference_steps: 5
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KMB8vhqlXLdAcElPz8lcQhtJrzzOzJEsdwWfkXAyuhotbKwq/meisje_met_de_parel.webp",
  "width": 640,
  "height": 640,
  "prompt": "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
  "scheduler": "EulerDiscreteScheduler",
  "enable_lcm": false,
  "sdxl_weights": "nightvision-xl-0791",
  "pose_strength": 0.4,
  "canny_strength": 0.3,
  "depth_strength": 0.5,
  "guidance_scale": 5,
  "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
  "ip_adapter_scale": 0.8,
  "lcm_guidance_scale": 1.5,
  "num_inference_steps": 30,
  "enable_pose_controlnet": true,
  "enhance_nonface_region": true,
  "enable_canny_controlnet": true,
  "enable_depth_controlnet": false,
  "lcm_num_inference_steps": 5,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:6af8583c541261472e92155d87bba80d5ad98461665802f2ba196ac099aaedc9",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KMB8vhqlXLdAcElPz8lcQhtJrzzOzJEsdwWfkXAyuhotbKwq/meisje_met_de_parel.webp",
      width: 640,
      height: 640,
      prompt: "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
      scheduler: "EulerDiscreteScheduler",
      enable_lcm: false,
      sdxl_weights: "nightvision-xl-0791",
      pose_strength: 0.4,
      canny_strength: 0.3,
      depth_strength: 0.5,
      guidance_scale: 5,
      negative_prompt: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
      ip_adapter_scale: 0.8,
      lcm_guidance_scale: 1.5,
      num_inference_steps: 30,
      enable_pose_controlnet: true,
      enhance_nonface_region: true,
      enable_canny_controlnet: true,
      enable_depth_controlnet: false,
      lcm_num_inference_steps: 5,
      controlnet_conditioning_scale: 0.8
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:6af8583c541261472e92155d87bba80d5ad98461665802f2ba196ac099aaedc9",
    input={
        "image": "https://replicate.delivery/pbxt/KMB8vhqlXLdAcElPz8lcQhtJrzzOzJEsdwWfkXAyuhotbKwq/meisje_met_de_parel.webp",
        "width": 640,
        "height": 640,
        "prompt": "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
        "scheduler": "EulerDiscreteScheduler",
        "enable_lcm": False,
        "sdxl_weights": "nightvision-xl-0791",
        "pose_strength": 0.4,
        "canny_strength": 0.3,
        "depth_strength": 0.5,
        "guidance_scale": 5,
        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
        "ip_adapter_scale": 0.8,
        "lcm_guidance_scale": 1.5,
        "num_inference_steps": 30,
        "enable_pose_controlnet": True,
        "enhance_nonface_region": True,
        "enable_canny_controlnet": True,
        "enable_depth_controlnet": False,
        "lcm_num_inference_steps": 5,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:6af8583c541261472e92155d87bba80d5ad98461665802f2ba196ac099aaedc9",
    "input": {
      "image": "https://replicate.delivery/pbxt/KMB8vhqlXLdAcElPz8lcQhtJrzzOzJEsdwWfkXAyuhotbKwq/meisje_met_de_parel.webp",
      "width": 640,
      "height": 640,
      "prompt": "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
      "scheduler": "EulerDiscreteScheduler",
      "enable_lcm": false,
      "sdxl_weights": "nightvision-xl-0791",
      "pose_strength": 0.4,
      "canny_strength": 0.3,
      "depth_strength": 0.5,
      "guidance_scale": 5,
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
      "ip_adapter_scale": 0.8,
      "lcm_guidance_scale": 1.5,
      "num_inference_steps": 30,
      "enable_pose_controlnet": true,
      "enhance_nonface_region": true,
      "enable_canny_controlnet": true,
      "enable_depth_controlnet": false,
      "lcm_num_inference_steps": 5,
      "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": "2024-02-06T14:05:12.172734Z",
  "created_at": "2024-02-06T14:04:25.076266Z",
  "data_removed": false,
  "error": null,
  "id": "r766fk3ban74fwagxopi7mqsxe",
  "input": {
    "image": "https://replicate.delivery/pbxt/KMB8vhqlXLdAcElPz8lcQhtJrzzOzJEsdwWfkXAyuhotbKwq/meisje_met_de_parel.webp",
    "width": 640,
    "height": 640,
    "prompt": "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
    "scheduler": "EulerDiscreteScheduler",
    "enable_lcm": false,
    "sdxl_weights": "nightvision-xl-0791",
    "pose_strength": 0.4,
    "canny_strength": 0.3,
    "depth_strength": 0.5,
    "guidance_scale": 5,
    "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
    "ip_adapter_scale": 0.8,
    "lcm_guidance_scale": 1.5,
    "num_inference_steps": 30,
    "enable_pose_controlnet": true,
    "enhance_nonface_region": true,
    "enable_canny_controlnet": true,
    "enable_depth_controlnet": false,
    "lcm_num_inference_steps": 5,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "Using seed: 31094\ndownloading url:  https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar\ndownloading to:  checkpoints/models--stablediffusionapi--nightvision-xl-0791\n2024-02-06T14:04:25Z | INFO  | [ Initiating ] dest=checkpoints/models--stablediffusionapi--nightvision-xl-0791 minimum_chunk_size=150M url=https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar\n2024-02-06T14:04:33Z | INFO  | [ Complete ] dest=checkpoints/models--stablediffusionapi--nightvision-xl-0791 size=\"6.9 GB\" total_elapsed=8.690s url=https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar\ndownloading took:  9.307956218719482\n[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--nightvision-xl-0791/\nKeyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.\nLoading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...:  14%|█▍        | 1/7 [00:00<00:02,  2.25it/s]\nLoading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00,  5.65it/s]\nLoading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00,  4.84it/s]\nLoading pipeline components...:  86%|████████▌ | 6/7 [00:02<00:00,  1.65it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:02<00:00,  2.42it/s]\n[~] Seting up LCM (just in case)\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\nStart inference...\n[Debug] Prompt: masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished,\n[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:16,  1.79it/s]\n  7%|▋         | 2/30 [00:01<00:15,  1.79it/s]\n 10%|█         | 3/30 [00:01<00:15,  1.79it/s]\n 13%|█▎        | 4/30 [00:02<00:14,  1.78it/s]\n 17%|█▋        | 5/30 [00:02<00:14,  1.78it/s]\n 20%|██        | 6/30 [00:03<00:13,  1.78it/s]\n 23%|██▎       | 7/30 [00:03<00:12,  1.78it/s]\n 27%|██▋       | 8/30 [00:04<00:12,  1.78it/s]\n 30%|███       | 9/30 [00:05<00:11,  1.78it/s]\n 33%|███▎      | 10/30 [00:05<00:11,  1.77it/s]\n 37%|███▋      | 11/30 [00:06<00:10,  1.77it/s]\n 40%|████      | 12/30 [00:06<00:10,  1.77it/s]\n 43%|████▎     | 13/30 [00:07<00:09,  1.77it/s]\n 47%|████▋     | 14/30 [00:07<00:09,  1.77it/s]\n 50%|█████     | 15/30 [00:08<00:08,  1.77it/s]\n 53%|█████▎    | 16/30 [00:09<00:07,  1.77it/s]\n 57%|█████▋    | 17/30 [00:09<00:07,  1.77it/s]\n 60%|██████    | 18/30 [00:10<00:06,  1.77it/s]\n 63%|██████▎   | 19/30 [00:10<00:06,  1.77it/s]\n 67%|██████▋   | 20/30 [00:11<00:05,  1.77it/s]\n 70%|███████   | 21/30 [00:11<00:05,  1.77it/s]\n 73%|███████▎  | 22/30 [00:12<00:04,  1.77it/s]\n 77%|███████▋  | 23/30 [00:12<00:03,  1.77it/s]\n 80%|████████  | 24/30 [00:13<00:03,  1.77it/s]\n 83%|████████▎ | 25/30 [00:14<00:02,  1.77it/s]\n 87%|████████▋ | 26/30 [00:14<00:02,  1.77it/s]\n 90%|█████████ | 27/30 [00:15<00:01,  1.77it/s]\n 93%|█████████▎| 28/30 [00:15<00:01,  1.77it/s]\n 97%|█████████▋| 29/30 [00:16<00:00,  1.77it/s]\n100%|██████████| 30/30 [00:16<00:00,  1.77it/s]\n100%|██████████| 30/30 [00:16<00:00,  1.77it/s]\nNSFW content detected: False",
  "metrics": {
    "predict_time": 47.065249,
    "total_time": 47.096468
  },
  "output": [
    "https://replicate.delivery/pbxt/AhtyoJfezztMUEvhkEXKKdeefqHLLqGF3emHkL7fQdIXLdfTSA/out_0.png"
  ],
  "started_at": "2024-02-06T14:04:25.107485Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/r766fk3ban74fwagxopi7mqsxe",
    "cancel": "https://api.replicate.com/v1/predictions/r766fk3ban74fwagxopi7mqsxe/cancel"
  },
  "version": "6af8583c541261472e92155d87bba80d5ad98461665802f2ba196ac099aaedc9"
}

Generated in

47.1 seconds

Tweak it ShareReport

Using seed: 31094
downloading url:  https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar
downloading to:  checkpoints/models--stablediffusionapi--nightvision-xl-0791
2024-02-06T14:04:25Z | INFO  | [ Initiating ] dest=checkpoints/models--stablediffusionapi--nightvision-xl-0791 minimum_chunk_size=150M url=https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar
2024-02-06T14:04:33Z | INFO  | [ Complete ] dest=checkpoints/models--stablediffusionapi--nightvision-xl-0791 size="6.9 GB" total_elapsed=8.690s url=https://weights.replicate.delivery/default/InstantID/models--stablediffusionapi--nightvision-xl-0791.tar
downloading took:  9.307956218719482
[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--nightvision-xl-0791/
Keyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:02,  2.25it/s]
Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00,  5.65it/s]
Loading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00,  4.84it/s]
Loading pipeline components...:  86%|████████▌ | 6/7 [00:02<00:00,  1.65it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:02<00:00,  2.42it/s]
[~] Seting up LCM (just in case)
/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.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
Start inference...
[Debug] Prompt: masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, picture of woman, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished,
[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:16,  1.79it/s]
  7%|▋         | 2/30 [00:01<00:15,  1.79it/s]
 10%|█         | 3/30 [00:01<00:15,  1.79it/s]
 13%|█▎        | 4/30 [00:02<00:14,  1.78it/s]
 17%|█▋        | 5/30 [00:02<00:14,  1.78it/s]
 20%|██        | 6/30 [00:03<00:13,  1.78it/s]
 23%|██▎       | 7/30 [00:03<00:12,  1.78it/s]
 27%|██▋       | 8/30 [00:04<00:12,  1.78it/s]
 30%|███       | 9/30 [00:05<00:11,  1.78it/s]
 33%|███▎      | 10/30 [00:05<00:11,  1.77it/s]
 37%|███▋      | 11/30 [00:06<00:10,  1.77it/s]
 40%|████      | 12/30 [00:06<00:10,  1.77it/s]
 43%|████▎     | 13/30 [00:07<00:09,  1.77it/s]
 47%|████▋     | 14/30 [00:07<00:09,  1.77it/s]
 50%|█████     | 15/30 [00:08<00:08,  1.77it/s]
 53%|█████▎    | 16/30 [00:09<00:07,  1.77it/s]
 57%|█████▋    | 17/30 [00:09<00:07,  1.77it/s]
 60%|██████    | 18/30 [00:10<00:06,  1.77it/s]
 63%|██████▎   | 19/30 [00:10<00:06,  1.77it/s]
 67%|██████▋   | 20/30 [00:11<00:05,  1.77it/s]
 70%|███████   | 21/30 [00:11<00:05,  1.77it/s]
 73%|███████▎  | 22/30 [00:12<00:04,  1.77it/s]
 77%|███████▋  | 23/30 [00:12<00:03,  1.77it/s]
 80%|████████  | 24/30 [00:13<00:03,  1.77it/s]
 83%|████████▎ | 25/30 [00:14<00:02,  1.77it/s]
 87%|████████▋ | 26/30 [00:14<00:02,  1.77it/s]
 90%|█████████ | 27/30 [00:15<00:01,  1.77it/s]
 93%|█████████▎| 28/30 [00:15<00:01,  1.77it/s]
 97%|█████████▋| 29/30 [00:16<00:00,  1.77it/s]
100%|██████████| 30/30 [00:16<00:00,  1.77it/s]
100%|██████████| 30/30 [00:16<00:00,  1.77it/s]
NSFW content detected: False

Prediction

zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63

Model

zsxkib/instant-id:f1ca369d

nqgnbwp069rgg0cfs79rpergec

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

36.1s

Created

about 1 year ago by @zsxkib

Input

image
prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality
scheduler: EulerDiscreteScheduler
enable_lcm
pose_image
num_outputs: 1
sdxl_weights: protovision-xl-high-fidel
output_format: webp
pose_strength: 0.4
canny_strength: 0.3
depth_strength: 0.5
guidance_scale: 5
output_quality: 80
negative_prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured
ip_adapter_scale: 0.8
lcm_guidance_scale: 1.5
num_inference_steps: 30
enable_pose_controlnet
enhance_nonface_region
enable_canny_controlnet
enable_depth_controlnet
lcm_num_inference_steps: 5
face_detection_input_width: 640
face_detection_input_height: 640
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
  "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
  "scheduler": "EulerDiscreteScheduler",
  "enable_lcm": false,
  "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
  "num_outputs": 1,
  "sdxl_weights": "protovision-xl-high-fidel",
  "output_format": "webp",
  "pose_strength": 0.4,
  "canny_strength": 0.3,
  "depth_strength": 0.5,
  "guidance_scale": 5,
  "output_quality": 80,
  "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
  "ip_adapter_scale": 0.8,
  "lcm_guidance_scale": 1.5,
  "num_inference_steps": 30,
  "enable_pose_controlnet": true,
  "enhance_nonface_region": true,
  "enable_canny_controlnet": false,
  "enable_depth_controlnet": false,
  "lcm_num_inference_steps": 5,
  "face_detection_input_width": 640,
  "face_detection_input_height": 640,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
      prompt: "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
      scheduler: "EulerDiscreteScheduler",
      enable_lcm: false,
      pose_image: "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
      num_outputs: 1,
      sdxl_weights: "protovision-xl-high-fidel",
      output_format: "webp",
      pose_strength: 0.4,
      canny_strength: 0.3,
      depth_strength: 0.5,
      guidance_scale: 5,
      output_quality: 80,
      negative_prompt: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      ip_adapter_scale: 0.8,
      lcm_guidance_scale: 1.5,
      num_inference_steps: 30,
      enable_pose_controlnet: true,
      enhance_nonface_region: true,
      enable_canny_controlnet: false,
      enable_depth_controlnet: false,
      lcm_num_inference_steps: 5,
      face_detection_input_width: 640,
      face_detection_input_height: 640,
      controlnet_conditioning_scale: 0.8
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
    input={
        "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
        "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
        "scheduler": "EulerDiscreteScheduler",
        "enable_lcm": False,
        "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
        "num_outputs": 1,
        "sdxl_weights": "protovision-xl-high-fidel",
        "output_format": "webp",
        "pose_strength": 0.4,
        "canny_strength": 0.3,
        "depth_strength": 0.5,
        "guidance_scale": 5,
        "output_quality": 80,
        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
        "ip_adapter_scale": 0.8,
        "lcm_guidance_scale": 1.5,
        "num_inference_steps": 30,
        "enable_pose_controlnet": True,
        "enhance_nonface_region": True,
        "enable_canny_controlnet": False,
        "enable_depth_controlnet": False,
        "lcm_num_inference_steps": 5,
        "face_detection_input_width": 640,
        "face_detection_input_height": 640,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
    "input": {
      "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
      "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
      "scheduler": "EulerDiscreteScheduler",
      "enable_lcm": false,
      "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
      "num_outputs": 1,
      "sdxl_weights": "protovision-xl-high-fidel",
      "output_format": "webp",
      "pose_strength": 0.4,
      "canny_strength": 0.3,
      "depth_strength": 0.5,
      "guidance_scale": 5,
      "output_quality": 80,
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      "ip_adapter_scale": 0.8,
      "lcm_guidance_scale": 1.5,
      "num_inference_steps": 30,
      "enable_pose_controlnet": true,
      "enhance_nonface_region": true,
      "enable_canny_controlnet": false,
      "enable_depth_controlnet": false,
      "lcm_num_inference_steps": 5,
      "face_detection_input_width": 640,
      "face_detection_input_height": 640,
      "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": "2024-05-30T14:08:04.881557Z",
  "created_at": "2024-05-30T14:07:28.818000Z",
  "data_removed": false,
  "error": null,
  "id": "nqgnbwp069rgg0cfs79rpergec",
  "input": {
    "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
    "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
    "scheduler": "EulerDiscreteScheduler",
    "enable_lcm": false,
    "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
    "num_outputs": 1,
    "sdxl_weights": "protovision-xl-high-fidel",
    "output_format": "webp",
    "pose_strength": 0.4,
    "canny_strength": 0.3,
    "depth_strength": 0.5,
    "guidance_scale": 5,
    "output_quality": 80,
    "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
    "ip_adapter_scale": 0.8,
    "lcm_guidance_scale": 1.5,
    "num_inference_steps": 30,
    "enable_pose_controlnet": true,
    "enhance_nonface_region": true,
    "enable_canny_controlnet": false,
    "enable_depth_controlnet": false,
    "lcm_num_inference_steps": 5,
    "face_detection_input_width": 640,
    "face_detection_input_height": 640,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "Using seed: 25815\n[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--protovision-xl-high-fidel/\nKeyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.\nLoading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  5.96it/s]\nLoading pipeline components...:  43%|████▎     | 3/7 [00:00<00:01,  3.94it/s]\nLoading pipeline components...:  71%|███████▏  | 5/7 [00:04<00:02,  1.15s/it]\nLoading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.48it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.50it/s]\n[~] Seting up LCM (just in case)\nStart inference...\n[Debug] Prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality,\n[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:07,  4.12it/s]\n  7%|▋         | 2/30 [00:00<00:06,  4.12it/s]\n 10%|█         | 3/30 [00:00<00:06,  4.13it/s]\n 13%|█▎        | 4/30 [00:00<00:06,  4.12it/s]\n 17%|█▋        | 5/30 [00:01<00:06,  4.12it/s]\n 20%|██        | 6/30 [00:01<00:05,  4.12it/s]\n 23%|██▎       | 7/30 [00:01<00:05,  4.12it/s]\n 27%|██▋       | 8/30 [00:01<00:05,  4.12it/s]\n 30%|███       | 9/30 [00:02<00:05,  4.12it/s]\n 33%|███▎      | 10/30 [00:02<00:04,  4.12it/s]\n 37%|███▋      | 11/30 [00:02<00:04,  4.12it/s]\n 40%|████      | 12/30 [00:02<00:04,  4.12it/s]\n 43%|████▎     | 13/30 [00:03<00:04,  4.12it/s]\n 47%|████▋     | 14/30 [00:03<00:03,  4.12it/s]\n 50%|█████     | 15/30 [00:03<00:03,  4.12it/s]\n 53%|█████▎    | 16/30 [00:03<00:03,  4.12it/s]\n 57%|█████▋    | 17/30 [00:04<00:03,  4.12it/s]\n 60%|██████    | 18/30 [00:04<00:02,  4.12it/s]\n 63%|██████▎   | 19/30 [00:04<00:02,  4.11it/s]\n 67%|██████▋   | 20/30 [00:04<00:02,  4.11it/s]\n 70%|███████   | 21/30 [00:05<00:02,  4.10it/s]\n 73%|███████▎  | 22/30 [00:05<00:01,  4.10it/s]\n 77%|███████▋  | 23/30 [00:05<00:01,  4.10it/s]\n 80%|████████  | 24/30 [00:05<00:01,  4.09it/s]\n 83%|████████▎ | 25/30 [00:06<00:01,  4.10it/s]\n 87%|████████▋ | 26/30 [00:06<00:00,  4.10it/s]\n 90%|█████████ | 27/30 [00:06<00:00,  4.10it/s]\n 93%|█████████▎| 28/30 [00:06<00:00,  4.09it/s]\n 97%|█████████▋| 29/30 [00:07<00:00,  4.09it/s]\n100%|██████████| 30/30 [00:07<00:00,  4.09it/s]\n100%|██████████| 30/30 [00:07<00:00,  4.11it/s]\nNSFW content detected: False\n[~] Saving to /tmp/out_0.webp...\n[~] Output format: WEBP\n[~] Output quality: 80",
  "metrics": {
    "predict_time": 36.017849,
    "total_time": 36.063557
  },
  "output": [
    "https://replicate.delivery/pbxt/J6l9A4W5SWK6NNTh9XXln5N6mk9Ge9FfMlC547bLezyISHzlA/out_0.webp"
  ],
  "started_at": "2024-05-30T14:07:28.863708Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nqgnbwp069rgg0cfs79rpergec",
    "cancel": "https://api.replicate.com/v1/predictions/nqgnbwp069rgg0cfs79rpergec/cancel"
  },
  "version": "f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63"
}

Generated in

36.0 seconds

Tweak it ShareReport

Using seed: 25815
[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--protovision-xl-high-fidel/
Keyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  5.96it/s]
Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:01,  3.94it/s]
Loading pipeline components...:  71%|███████▏  | 5/7 [00:04<00:02,  1.15s/it]
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.48it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.50it/s]
[~] Seting up LCM (just in case)
Start inference...
[Debug] Prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality,
[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  4.12it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.12it/s]
 10%|█         | 3/30 [00:00<00:06,  4.13it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.12it/s]
 17%|█▋        | 5/30 [00:01<00:06,  4.12it/s]
 20%|██        | 6/30 [00:01<00:05,  4.12it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.12it/s]
 27%|██▋       | 8/30 [00:01<00:05,  4.12it/s]
 30%|███       | 9/30 [00:02<00:05,  4.12it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.12it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.12it/s]
 40%|████      | 12/30 [00:02<00:04,  4.12it/s]
 43%|████▎     | 13/30 [00:03<00:04,  4.12it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.12it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.12it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.12it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  4.12it/s]
 60%|██████    | 18/30 [00:04<00:02,  4.12it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.11it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.11it/s]
 70%|███████   | 21/30 [00:05<00:02,  4.10it/s]
 73%|███████▎  | 22/30 [00:05<00:01,  4.10it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.10it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.09it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  4.10it/s]
 87%|████████▋ | 26/30 [00:06<00:00,  4.10it/s]
 90%|█████████ | 27/30 [00:06<00:00,  4.10it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.09it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  4.09it/s]
100%|██████████| 30/30 [00:07<00:00,  4.09it/s]
100%|██████████| 30/30 [00:07<00:00,  4.11it/s]
NSFW content detected: False
[~] Saving to /tmp/out_0.webp...
[~] Output format: WEBP
[~] Output quality: 80

Prediction

zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63

Model

zsxkib/instant-id:f1ca369d

nqgnbwp069rgg0cfs79rpergec

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

36.1s

Created

about 1 year ago by @zsxkib

Input

image
prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality
scheduler: EulerDiscreteScheduler
enable_lcm
pose_image
num_outputs: 1
sdxl_weights: protovision-xl-high-fidel
output_format: webp
pose_strength: 0.4
canny_strength: 0.3
depth_strength: 0.5
guidance_scale: 5
output_quality: 80
negative_prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured
ip_adapter_scale: 0.8
lcm_guidance_scale: 1.5
num_inference_steps: 30
enable_pose_controlnet
enhance_nonface_region
enable_canny_controlnet
enable_depth_controlnet
lcm_num_inference_steps: 5
face_detection_input_width: 640
face_detection_input_height: 640
controlnet_conditioning_scale: 0.8

{
  "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
  "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
  "scheduler": "EulerDiscreteScheduler",
  "enable_lcm": false,
  "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
  "num_outputs": 1,
  "sdxl_weights": "protovision-xl-high-fidel",
  "output_format": "webp",
  "pose_strength": 0.4,
  "canny_strength": 0.3,
  "depth_strength": 0.5,
  "guidance_scale": 5,
  "output_quality": 80,
  "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
  "ip_adapter_scale": 0.8,
  "lcm_guidance_scale": 1.5,
  "num_inference_steps": 30,
  "enable_pose_controlnet": true,
  "enhance_nonface_region": true,
  "enable_canny_controlnet": false,
  "enable_depth_controlnet": false,
  "lcm_num_inference_steps": 5,
  "face_detection_input_width": 640,
  "face_detection_input_height": 640,
  "controlnet_conditioning_scale": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
      prompt: "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
      scheduler: "EulerDiscreteScheduler",
      enable_lcm: false,
      pose_image: "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
      num_outputs: 1,
      sdxl_weights: "protovision-xl-high-fidel",
      output_format: "webp",
      pose_strength: 0.4,
      canny_strength: 0.3,
      depth_strength: 0.5,
      guidance_scale: 5,
      output_quality: 80,
      negative_prompt: "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      ip_adapter_scale: 0.8,
      lcm_guidance_scale: 1.5,
      num_inference_steps: 30,
      enable_pose_controlnet: true,
      enhance_nonface_region: true,
      enable_canny_controlnet: false,
      enable_depth_controlnet: false,
      lcm_num_inference_steps: 5,
      face_detection_input_width: 640,
      face_detection_input_height: 640,
      controlnet_conditioning_scale: 0.8
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
    input={
        "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
        "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
        "scheduler": "EulerDiscreteScheduler",
        "enable_lcm": False,
        "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
        "num_outputs": 1,
        "sdxl_weights": "protovision-xl-high-fidel",
        "output_format": "webp",
        "pose_strength": 0.4,
        "canny_strength": 0.3,
        "depth_strength": 0.5,
        "guidance_scale": 5,
        "output_quality": 80,
        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
        "ip_adapter_scale": 0.8,
        "lcm_guidance_scale": 1.5,
        "num_inference_steps": 30,
        "enable_pose_controlnet": True,
        "enhance_nonface_region": True,
        "enable_canny_controlnet": False,
        "enable_depth_controlnet": False,
        "lcm_num_inference_steps": 5,
        "face_detection_input_width": 640,
        "face_detection_input_height": 640,
        "controlnet_conditioning_scale": 0.8
    }
)
print(output)

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

Run zsxkib/instant-id 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": "zsxkib/instant-id:f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63",
    "input": {
      "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
      "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
      "scheduler": "EulerDiscreteScheduler",
      "enable_lcm": false,
      "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
      "num_outputs": 1,
      "sdxl_weights": "protovision-xl-high-fidel",
      "output_format": "webp",
      "pose_strength": 0.4,
      "canny_strength": 0.3,
      "depth_strength": 0.5,
      "guidance_scale": 5,
      "output_quality": 80,
      "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
      "ip_adapter_scale": 0.8,
      "lcm_guidance_scale": 1.5,
      "num_inference_steps": 30,
      "enable_pose_controlnet": true,
      "enhance_nonface_region": true,
      "enable_canny_controlnet": false,
      "enable_depth_controlnet": false,
      "lcm_num_inference_steps": 5,
      "face_detection_input_width": 640,
      "face_detection_input_height": 640,
      "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": "2024-05-30T14:08:04.881557Z",
  "created_at": "2024-05-30T14:07:28.818000Z",
  "data_removed": false,
  "error": null,
  "id": "nqgnbwp069rgg0cfs79rpergec",
  "input": {
    "image": "https://replicate.delivery/pbxt/KIIutO7jIleskKaWebhvurgBUlHR6M6KN7KHaMMWSt4OnVrF/musk_resize.jpeg",
    "prompt": "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
    "scheduler": "EulerDiscreteScheduler",
    "enable_lcm": false,
    "pose_image": "https://replicate.delivery/pbxt/KJmFdQRQVDXGDVdVXftLvFrrvgOPXXRXbzIVEyExPYYOFPyF/80048a6e6586759dbcb529e74a9042ca.jpeg",
    "num_outputs": 1,
    "sdxl_weights": "protovision-xl-high-fidel",
    "output_format": "webp",
    "pose_strength": 0.4,
    "canny_strength": 0.3,
    "depth_strength": 0.5,
    "guidance_scale": 5,
    "output_quality": 80,
    "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured",
    "ip_adapter_scale": 0.8,
    "lcm_guidance_scale": 1.5,
    "num_inference_steps": 30,
    "enable_pose_controlnet": true,
    "enhance_nonface_region": true,
    "enable_canny_controlnet": false,
    "enable_depth_controlnet": false,
    "lcm_num_inference_steps": 5,
    "face_detection_input_width": 640,
    "face_detection_input_height": 640,
    "controlnet_conditioning_scale": 0.8
  },
  "logs": "Using seed: 25815\n[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--protovision-xl-high-fidel/\nKeyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.\nLoading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  5.96it/s]\nLoading pipeline components...:  43%|████▎     | 3/7 [00:00<00:01,  3.94it/s]\nLoading pipeline components...:  71%|███████▏  | 5/7 [00:04<00:02,  1.15s/it]\nLoading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.48it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.50it/s]\n[~] Seting up LCM (just in case)\nStart inference...\n[Debug] Prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality,\n[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:07,  4.12it/s]\n  7%|▋         | 2/30 [00:00<00:06,  4.12it/s]\n 10%|█         | 3/30 [00:00<00:06,  4.13it/s]\n 13%|█▎        | 4/30 [00:00<00:06,  4.12it/s]\n 17%|█▋        | 5/30 [00:01<00:06,  4.12it/s]\n 20%|██        | 6/30 [00:01<00:05,  4.12it/s]\n 23%|██▎       | 7/30 [00:01<00:05,  4.12it/s]\n 27%|██▋       | 8/30 [00:01<00:05,  4.12it/s]\n 30%|███       | 9/30 [00:02<00:05,  4.12it/s]\n 33%|███▎      | 10/30 [00:02<00:04,  4.12it/s]\n 37%|███▋      | 11/30 [00:02<00:04,  4.12it/s]\n 40%|████      | 12/30 [00:02<00:04,  4.12it/s]\n 43%|████▎     | 13/30 [00:03<00:04,  4.12it/s]\n 47%|████▋     | 14/30 [00:03<00:03,  4.12it/s]\n 50%|█████     | 15/30 [00:03<00:03,  4.12it/s]\n 53%|█████▎    | 16/30 [00:03<00:03,  4.12it/s]\n 57%|█████▋    | 17/30 [00:04<00:03,  4.12it/s]\n 60%|██████    | 18/30 [00:04<00:02,  4.12it/s]\n 63%|██████▎   | 19/30 [00:04<00:02,  4.11it/s]\n 67%|██████▋   | 20/30 [00:04<00:02,  4.11it/s]\n 70%|███████   | 21/30 [00:05<00:02,  4.10it/s]\n 73%|███████▎  | 22/30 [00:05<00:01,  4.10it/s]\n 77%|███████▋  | 23/30 [00:05<00:01,  4.10it/s]\n 80%|████████  | 24/30 [00:05<00:01,  4.09it/s]\n 83%|████████▎ | 25/30 [00:06<00:01,  4.10it/s]\n 87%|████████▋ | 26/30 [00:06<00:00,  4.10it/s]\n 90%|█████████ | 27/30 [00:06<00:00,  4.10it/s]\n 93%|█████████▎| 28/30 [00:06<00:00,  4.09it/s]\n 97%|█████████▋| 29/30 [00:07<00:00,  4.09it/s]\n100%|██████████| 30/30 [00:07<00:00,  4.09it/s]\n100%|██████████| 30/30 [00:07<00:00,  4.11it/s]\nNSFW content detected: False\n[~] Saving to /tmp/out_0.webp...\n[~] Output format: WEBP\n[~] Output quality: 80",
  "metrics": {
    "predict_time": 36.017849,
    "total_time": 36.063557
  },
  "output": [
    "https://replicate.delivery/pbxt/J6l9A4W5SWK6NNTh9XXln5N6mk9Ge9FfMlC547bLezyISHzlA/out_0.webp"
  ],
  "started_at": "2024-05-30T14:07:28.863708Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nqgnbwp069rgg0cfs79rpergec",
    "cancel": "https://api.replicate.com/v1/predictions/nqgnbwp069rgg0cfs79rpergec/cancel"
  },
  "version": "f1ca369da43885a347690a98f6b710afbf5f167cb9bf13bd5af512ba4a9f7b63"
}

Generated in

36.0 seconds

Tweak it ShareReport

Using seed: 25815
[~] Loading new SDXL weights: checkpoints/models--stablediffusionapi--protovision-xl-high-fidel/
Keyword arguments {'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  5.96it/s]
Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:01,  3.94it/s]
Loading pipeline components...:  71%|███████▏  | 5/7 [00:04<00:02,  1.15s/it]
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.48it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.50it/s]
[~] Seting up LCM (just in case)
Start inference...
[Debug] Prompt: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality,
[Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  4.12it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.12it/s]
 10%|█         | 3/30 [00:00<00:06,  4.13it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.12it/s]
 17%|█▋        | 5/30 [00:01<00:06,  4.12it/s]
 20%|██        | 6/30 [00:01<00:05,  4.12it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.12it/s]
 27%|██▋       | 8/30 [00:01<00:05,  4.12it/s]
 30%|███       | 9/30 [00:02<00:05,  4.12it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.12it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.12it/s]
 40%|████      | 12/30 [00:02<00:04,  4.12it/s]
 43%|████▎     | 13/30 [00:03<00:04,  4.12it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.12it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.12it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.12it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  4.12it/s]
 60%|██████    | 18/30 [00:04<00:02,  4.12it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.11it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.11it/s]
 70%|███████   | 21/30 [00:05<00:02,  4.10it/s]
 73%|███████▎  | 22/30 [00:05<00:01,  4.10it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.10it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.09it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  4.10it/s]
 87%|████████▋ | 26/30 [00:06<00:00,  4.10it/s]
 90%|█████████ | 27/30 [00:06<00:00,  4.10it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.09it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  4.09it/s]
100%|██████████| 30/30 [00:07<00:00,  4.09it/s]
100%|██████████| 30/30 [00:07<00:00,  4.11it/s]
NSFW content detected: False
[~] Saving to /tmp/out_0.webp...
[~] Output format: WEBP
[~] Output quality: 80

Want to make some of these yourself?

Run this model