zsxkib/instant-id:2e4785a4 – Run with an API on Replicate

Version

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

zsxkib /instant-id:2e4785a4

Playground API

Input

image

*file

Preview

Input face image

pose_image

file

Preview

(Optional) reference pose image

prompt

string

Shift + Return to add a new line

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

Input prompt

Default: "a person"

negative_prompt

string

Shift + Return to add a new line

(lowres, low quality, worst quality:1.2), (text:1.2), watermark, 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(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

Input Negative Prompt

Default: ""

sdxl_weights

string

Pick which base weights you want to use

Default: "stable-diffusion-xl-base-1.0"

face_detection_input_width

integer

(minimum: 640, maximum: 4096)

Width of the input image for face detection

Default: 640

face_detection_input_height

integer

(minimum: 640, maximum: 4096)

Height of the input image for face detection

Default: 640

scheduler

string

Scheduler

Default: "EulerDiscreteScheduler"

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: 7.5

ip_adapter_scale

number

(minimum: 0, maximum: 1.5)

Scale for image adapter strength (for detail)

Default: 0.8

controlnet_conditioning_scale

number

(minimum: 0, maximum: 1.5)

Scale for IdentityNet strength (for fidelity)

Default: 0.8

enable_pose_controlnet

boolean

Enable Openpose ControlNet, overrides strength if set to false

Default: true

pose_strength

number

(minimum: 0, maximum: 1)

Openpose ControlNet strength, effective only if `enable_pose_controlnet` is true

Default: 0.4

enable_canny_controlnet

boolean

Enable Canny ControlNet, overrides strength if set to false

Default: false

canny_strength

number

(minimum: 0, maximum: 1)

Canny ControlNet strength, effective only if `enable_canny_controlnet` is true

Default: 0.3

enable_depth_controlnet

boolean

Enable Depth ControlNet, overrides strength if set to false

Default: false

depth_strength

number

(minimum: 0, maximum: 1)

Depth ControlNet strength, effective only if `enable_depth_controlnet` is true

Default: 0.5

enable_lcm

boolean

Enable Fast Inference with LCM (Latent Consistency Models) - speeds up inference steps, trade-off is the quality of the generated image. Performs better with close-up portrait face images

Default: false

lcm_num_inference_steps

integer

(minimum: 1, maximum: 10)

Only used when `enable_lcm` is set to True, Number of denoising steps when using LCM

Default: 5

lcm_guidance_scale

number

(minimum: 1, maximum: 20)

Only used when `enable_lcm` is set to True, Scale for classifier-free guidance when using LCM

Default: 1.5

enhance_nonface_region

boolean

Enhance non-face region

Default: true

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

seed

integer

Random seed. Leave blank to randomize the seed

num_outputs

integer

(minimum: 1, maximum: 8)

Number of images to output

Default: 1

disable_safety_checker

boolean

Disable safety checker for generated images

Default: false

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

npx create-replicate --model=zsxkib/instant-id

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";

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:2e4785a4d80dadf580077b2244c8d7c05d8e3faac04a04c02d8e099dd2876789",
  {
    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
    }
  }
);
console.log(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 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:2e4785a4d80dadf580077b2244c8d7c05d8e3faac04a04c02d8e099dd2876789",
    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.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

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": "2e4785a4d80dadf580077b2244c8d7c05d8e3faac04a04c02d8e099dd2876789",
    "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

This example was created by a different version, zsxkib/instant-id:f1ca369d.