Prediction

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

Model

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

ID

nixvsb3byk2c73cm6hq32v4boq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

3m 16s

Created

about 2 years ago by @usamaehsan

Input

eta: 0
prompt: underwater++ world
max_width: 512
scheduler: DDIM
guess_mode
max_height: 512
num_outputs: 1
lineart_image: 955ad4a4680988283115264b5b45c211.jpg
guidance_scale: 7
negative_prompt: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
consistency_decoder
num_inference_steps: 20
disable_safety_check
tile_conditioning_scale: 1
depth_conditioning_scale: 1
lineart_conditioning_scale: 1
scribble_conditioning_scale: 1
brightness_conditioning_scale: 1
inpainting_conditioning_scale: 1

{
  "eta": 0,
  "prompt": "underwater++ world",
  "max_width": 512,
  "scheduler": "DDIM",
  "guess_mode": false,
  "max_height": 512,
  "num_outputs": 1,
  "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
  "guidance_scale": 7,
  "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "consistency_decoder": true,
  "num_inference_steps": 20,
  "disable_safety_check": true,
  "tile_conditioning_scale": 1,
  "depth_conditioning_scale": 1,
  "lineart_conditioning_scale": 1,
  "scribble_conditioning_scale": 1,
  "brightness_conditioning_scale": 1,
  "inpainting_conditioning_scale": 1
}

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 usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
  {
    input: {
      eta: 0,
      prompt: "underwater++ world",
      max_width: 512,
      scheduler: "DDIM",
      guess_mode: false,
      max_height: 512,
      num_outputs: 1,
      lineart_image: "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
      guidance_scale: 7,
      negative_prompt: "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      consistency_decoder: true,
      num_inference_steps: 20,
      disable_safety_check: true,
      tile_conditioning_scale: 1,
      depth_conditioning_scale: 1,
      lineart_conditioning_scale: 1,
      scribble_conditioning_scale: 1,
      brightness_conditioning_scale: 1,
      inpainting_conditioning_scale: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    input={
        "eta": 0,
        "prompt": "underwater++ world",
        "max_width": 512,
        "scheduler": "DDIM",
        "guess_mode": False,
        "max_height": 512,
        "num_outputs": 1,
        "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
        "guidance_scale": 7,
        "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "consistency_decoder": True,
        "num_inference_steps": 20,
        "disable_safety_check": True,
        "tile_conditioning_scale": 1,
        "depth_conditioning_scale": 1,
        "lineart_conditioning_scale": 1,
        "scribble_conditioning_scale": 1,
        "brightness_conditioning_scale": 1,
        "inpainting_conditioning_scale": 1
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    "input": {
      "eta": 0,
      "prompt": "underwater++ world",
      "max_width": 512,
      "scheduler": "DDIM",
      "guess_mode": false,
      "max_height": 512,
      "num_outputs": 1,
      "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
      "guidance_scale": 7,
      "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "consistency_decoder": true,
      "num_inference_steps": 20,
      "disable_safety_check": true,
      "tile_conditioning_scale": 1,
      "depth_conditioning_scale": 1,
      "lineart_conditioning_scale": 1,
      "scribble_conditioning_scale": 1,
      "brightness_conditioning_scale": 1,
      "inpainting_conditioning_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

seed-44665.png

{
  "completed_at": "2023-11-10T17:42:18.197496Z",
  "created_at": "2023-11-10T17:39:02.361897Z",
  "data_removed": false,
  "error": null,
  "id": "nixvsb3byk2c73cm6hq32v4boq",
  "input": {
    "eta": 0,
    "prompt": "underwater++ world",
    "max_width": 512,
    "scheduler": "DDIM",
    "guess_mode": false,
    "max_height": 512,
    "num_outputs": 1,
    "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
    "guidance_scale": 7,
    "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "consistency_decoder": true,
    "num_inference_steps": 20,
    "disable_safety_check": true,
    "tile_conditioning_scale": 1,
    "depth_conditioning_scale": 1,
    "lineart_conditioning_scale": 1,
    "scribble_conditioning_scale": 1,
    "brightness_conditioning_scale": 1,
    "inpainting_conditioning_scale": 1
  },
  "logs": "You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .\nUsing seed: 44665\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:03,  4.83it/s]\n 20%|██        | 4/20 [00:00<00:01, 12.98it/s]\n 35%|███▌      | 7/20 [00:00<00:00, 16.54it/s]\n 50%|█████     | 10/20 [00:00<00:00, 18.42it/s]\n 60%|██████    | 12/20 [00:00<00:00, 18.76it/s]\n 70%|███████   | 14/20 [00:00<00:00, 18.86it/s]\n 85%|████████▌ | 17/20 [00:00<00:00, 19.89it/s]\n100%|██████████| 20/20 [00:01<00:00, 20.41it/s]\n100%|██████████| 20/20 [00:01<00:00, 18.04it/s]\nRunning consistency decoder...\nConsistency decoder took 11.307215690612793 seconds",
  "metrics": {
    "predict_time": 15.267783,
    "total_time": 195.835599
  },
  "output": [
    "https://replicate.delivery/pbxt/FMG5rpMM3GrCAVcfnqBFgNDb8mkSfA5mPg5mNJjwgaX51B3RA/seed-44665.png"
  ],
  "started_at": "2023-11-10T17:42:02.929713Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nixvsb3byk2c73cm6hq32v4boq",
    "cancel": "https://api.replicate.com/v1/predictions/nixvsb3byk2c73cm6hq32v4boq/cancel"
  },
  "version": "59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5"
}

Generated in

15.3 seconds

Tweak it Iterate in playground Share Report

Prediction

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

Model

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

ID

sdezdcdbquw6b4wuwr5dso26eq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

3.2s

Created

about 2 years ago

Input

eta: 0
prompt: underwater++ world
max_width: 512
scheduler: DDIM
guess_mode
max_height: 512
depth_image: 041bcb1be871434b3e31a5c0840c154a.jpg
num_outputs: 1
guidance_scale: 7
negative_prompt: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
consistency_decoder
num_inference_steps: 10
disable_safety_check
tile_conditioning_scale: 1
depth_conditioning_scale: 1
lineart_conditioning_scale: 1
scribble_conditioning_scale: 1
brightness_conditioning_scale: 1
inpainting_conditioning_scale: 1

{
  "eta": 0,
  "prompt": "underwater++ world",
  "max_width": 512,
  "scheduler": "DDIM",
  "guess_mode": false,
  "max_height": 512,
  "depth_image": "https://replicate.delivery/pbxt/Jr03Fvr8L1c8n9AvOEqeulpraXBOUR027a2KqY6EOC53SWZk/041bcb1be871434b3e31a5c0840c154a.jpg",
  "num_outputs": 1,
  "guidance_scale": 7,
  "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "consistency_decoder": true,
  "num_inference_steps": 10,
  "disable_safety_check": true,
  "tile_conditioning_scale": 1,
  "depth_conditioning_scale": 1,
  "lineart_conditioning_scale": 1,
  "scribble_conditioning_scale": 1,
  "brightness_conditioning_scale": 1,
  "inpainting_conditioning_scale": 1
}

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 usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
  {
    input: {
      eta: 0,
      prompt: "underwater++ world",
      max_width: 512,
      scheduler: "DDIM",
      guess_mode: false,
      max_height: 512,
      depth_image: "https://replicate.delivery/pbxt/Jr03Fvr8L1c8n9AvOEqeulpraXBOUR027a2KqY6EOC53SWZk/041bcb1be871434b3e31a5c0840c154a.jpg",
      num_outputs: 1,
      guidance_scale: 7,
      negative_prompt: "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      consistency_decoder: true,
      num_inference_steps: 10,
      disable_safety_check: true,
      tile_conditioning_scale: 1,
      depth_conditioning_scale: 1,
      lineart_conditioning_scale: 1,
      scribble_conditioning_scale: 1,
      brightness_conditioning_scale: 1,
      inpainting_conditioning_scale: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    input={
        "eta": 0,
        "prompt": "underwater++ world",
        "max_width": 512,
        "scheduler": "DDIM",
        "guess_mode": False,
        "max_height": 512,
        "depth_image": "https://replicate.delivery/pbxt/Jr03Fvr8L1c8n9AvOEqeulpraXBOUR027a2KqY6EOC53SWZk/041bcb1be871434b3e31a5c0840c154a.jpg",
        "num_outputs": 1,
        "guidance_scale": 7,
        "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "consistency_decoder": True,
        "num_inference_steps": 10,
        "disable_safety_check": True,
        "tile_conditioning_scale": 1,
        "depth_conditioning_scale": 1,
        "lineart_conditioning_scale": 1,
        "scribble_conditioning_scale": 1,
        "brightness_conditioning_scale": 1,
        "inpainting_conditioning_scale": 1
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    "input": {
      "eta": 0,
      "prompt": "underwater++ world",
      "max_width": 512,
      "scheduler": "DDIM",
      "guess_mode": false,
      "max_height": 512,
      "depth_image": "https://replicate.delivery/pbxt/Jr03Fvr8L1c8n9AvOEqeulpraXBOUR027a2KqY6EOC53SWZk/041bcb1be871434b3e31a5c0840c154a.jpg",
      "num_outputs": 1,
      "guidance_scale": 7,
      "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "consistency_decoder": true,
      "num_inference_steps": 10,
      "disable_safety_check": true,
      "tile_conditioning_scale": 1,
      "depth_conditioning_scale": 1,
      "lineart_conditioning_scale": 1,
      "scribble_conditioning_scale": 1,
      "brightness_conditioning_scale": 1,
      "inpainting_conditioning_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

seed-36662.png

{
  "completed_at": "2023-11-10T17:43:24.899404Z",
  "created_at": "2023-11-10T17:43:21.743511Z",
  "data_removed": false,
  "error": null,
  "id": "sdezdcdbquw6b4wuwr5dso26eq",
  "input": {
    "eta": 0,
    "prompt": "underwater++ world",
    "max_width": 512,
    "scheduler": "DDIM",
    "guess_mode": false,
    "max_height": 512,
    "depth_image": "https://replicate.delivery/pbxt/Jr03Fvr8L1c8n9AvOEqeulpraXBOUR027a2KqY6EOC53SWZk/041bcb1be871434b3e31a5c0840c154a.jpg",
    "num_outputs": 1,
    "guidance_scale": 7,
    "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "consistency_decoder": true,
    "num_inference_steps": 10,
    "disable_safety_check": true,
    "tile_conditioning_scale": 1,
    "depth_conditioning_scale": 1,
    "lineart_conditioning_scale": 1,
    "scribble_conditioning_scale": 1,
    "brightness_conditioning_scale": 1,
    "inpainting_conditioning_scale": 1
  },
  "logs": "You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .\nUsing seed: 36662\n  0%|          | 0/10 [00:00<?, ?it/s]\n 30%|███       | 3/10 [00:00<00:00, 20.71it/s]\n 60%|██████    | 6/10 [00:00<00:00, 21.13it/s]\n 90%|█████████ | 9/10 [00:00<00:00, 21.36it/s]\n100%|██████████| 10/10 [00:00<00:00, 21.26it/s]\nRunning consistency decoder...\nConsistency decoder took 0.5317535400390625 seconds",
  "metrics": {
    "predict_time": 3.190815,
    "total_time": 3.155893
  },
  "output": [
    "https://replicate.delivery/pbxt/hg0ArF8NKsKQLdTuLoIhHSQMaNZuOQbEDBQGRbtScbFvdwdE/seed-36662.png"
  ],
  "started_at": "2023-11-10T17:43:21.708589Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sdezdcdbquw6b4wuwr5dso26eq",
    "cancel": "https://api.replicate.com/v1/predictions/sdezdcdbquw6b4wuwr5dso26eq/cancel"
  },
  "version": "59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5"
}

Generated in

3.2 seconds

Tweak it Iterate in playground Share Report

Prediction

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

Model

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce

ID

tczw673btnldc2wz4rbqwkrf6i

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

3.6s

Created

about 2 years ago

Input

eta: 0
prompt: underwater++ universe
max_width: 512
scheduler: DDIM
guess_mode
max_height: 512
num_outputs: 1
guidance_scale: 7
scribble_image: 041bcb1be871434b3e31a5c0840c154a.jpg
negative_prompt: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
consistency_decoder
num_inference_steps: 10
disable_safety_check
tile_conditioning_scale: 1
depth_conditioning_scale: 1
lineart_conditioning_scale: 1
scribble_conditioning_scale: 1
brightness_conditioning_scale: 1
inpainting_conditioning_scale: 1

{
  "eta": 0,
  "prompt": "underwater++ universe",
  "max_width": 512,
  "scheduler": "DDIM",
  "guess_mode": false,
  "max_height": 512,
  "num_outputs": 1,
  "guidance_scale": 7,
  "scribble_image": "https://replicate.delivery/pbxt/Jr03x3Ldbbr97MoL87oDtXwEBprn9fDgfsYKRNOp4e24Jf7N/041bcb1be871434b3e31a5c0840c154a.jpg",
  "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "consistency_decoder": true,
  "num_inference_steps": 10,
  "disable_safety_check": true,
  "tile_conditioning_scale": 1,
  "depth_conditioning_scale": 1,
  "lineart_conditioning_scale": 1,
  "scribble_conditioning_scale": 1,
  "brightness_conditioning_scale": 1,
  "inpainting_conditioning_scale": 1
}

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 usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
  {
    input: {
      eta: 0,
      prompt: "underwater++ universe",
      max_width: 512,
      scheduler: "DDIM",
      guess_mode: false,
      max_height: 512,
      num_outputs: 1,
      guidance_scale: 7,
      scribble_image: "https://replicate.delivery/pbxt/Jr03x3Ldbbr97MoL87oDtXwEBprn9fDgfsYKRNOp4e24Jf7N/041bcb1be871434b3e31a5c0840c154a.jpg",
      negative_prompt: "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      consistency_decoder: true,
      num_inference_steps: 10,
      disable_safety_check: true,
      tile_conditioning_scale: 1,
      depth_conditioning_scale: 1,
      lineart_conditioning_scale: 1,
      scribble_conditioning_scale: 1,
      brightness_conditioning_scale: 1,
      inpainting_conditioning_scale: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    input={
        "eta": 0,
        "prompt": "underwater++ universe",
        "max_width": 512,
        "scheduler": "DDIM",
        "guess_mode": False,
        "max_height": 512,
        "num_outputs": 1,
        "guidance_scale": 7,
        "scribble_image": "https://replicate.delivery/pbxt/Jr03x3Ldbbr97MoL87oDtXwEBprn9fDgfsYKRNOp4e24Jf7N/041bcb1be871434b3e31a5c0840c154a.jpg",
        "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "consistency_decoder": True,
        "num_inference_steps": 10,
        "disable_safety_check": True,
        "tile_conditioning_scale": 1,
        "depth_conditioning_scale": 1,
        "lineart_conditioning_scale": 1,
        "scribble_conditioning_scale": 1,
        "brightness_conditioning_scale": 1,
        "inpainting_conditioning_scale": 1
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5",
    "input": {
      "eta": 0,
      "prompt": "underwater++ universe",
      "max_width": 512,
      "scheduler": "DDIM",
      "guess_mode": false,
      "max_height": 512,
      "num_outputs": 1,
      "guidance_scale": 7,
      "scribble_image": "https://replicate.delivery/pbxt/Jr03x3Ldbbr97MoL87oDtXwEBprn9fDgfsYKRNOp4e24Jf7N/041bcb1be871434b3e31a5c0840c154a.jpg",
      "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "consistency_decoder": true,
      "num_inference_steps": 10,
      "disable_safety_check": true,
      "tile_conditioning_scale": 1,
      "depth_conditioning_scale": 1,
      "lineart_conditioning_scale": 1,
      "scribble_conditioning_scale": 1,
      "brightness_conditioning_scale": 1,
      "inpainting_conditioning_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

seed-34345.png

{
  "completed_at": "2023-11-10T17:44:08.302198Z",
  "created_at": "2023-11-10T17:44:04.751222Z",
  "data_removed": false,
  "error": null,
  "id": "tczw673btnldc2wz4rbqwkrf6i",
  "input": {
    "eta": 0,
    "prompt": "underwater++ universe",
    "max_width": 512,
    "scheduler": "DDIM",
    "guess_mode": false,
    "max_height": 512,
    "num_outputs": 1,
    "guidance_scale": 7,
    "scribble_image": "https://replicate.delivery/pbxt/Jr03x3Ldbbr97MoL87oDtXwEBprn9fDgfsYKRNOp4e24Jf7N/041bcb1be871434b3e31a5c0840c154a.jpg",
    "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "consistency_decoder": true,
    "num_inference_steps": 10,
    "disable_safety_check": true,
    "tile_conditioning_scale": 1,
    "depth_conditioning_scale": 1,
    "lineart_conditioning_scale": 1,
    "scribble_conditioning_scale": 1,
    "brightness_conditioning_scale": 1,
    "inpainting_conditioning_scale": 1
  },
  "logs": "You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .\nUsing seed: 34345\n  0%|          | 0/10 [00:00<?, ?it/s]\n 30%|███       | 3/10 [00:00<00:00, 21.85it/s]\n 60%|██████    | 6/10 [00:00<00:00, 21.87it/s]\n 90%|█████████ | 9/10 [00:00<00:00, 21.92it/s]\n100%|██████████| 10/10 [00:00<00:00, 21.91it/s]\nRunning consistency decoder...\nConsistency decoder took 0.5318448543548584 seconds",
  "metrics": {
    "predict_time": 3.548575,
    "total_time": 3.550976
  },
  "output": [
    "https://replicate.delivery/pbxt/VW4lCy5b1fQjekOa3jCJBNTfGdltNfqNYsCqjxv3wEQceO4OC/seed-34345.png"
  ],
  "started_at": "2023-11-10T17:44:04.753623Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/tczw673btnldc2wz4rbqwkrf6i",
    "cancel": "https://api.replicate.com/v1/predictions/tczw673btnldc2wz4rbqwkrf6i/cancel"
  },
  "version": "59c1f5ce85cf1ea03e07508964ff41968cfad2a61820e3455930120ae2d594f5"
}

Generated in

3.5 seconds

Tweak it Iterate in playground Share Report

Prediction

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:a2d18c9c

Model

usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:a2d18c9c

ID

7q2acqdb3fd4hdjuutgvkk5aci

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2.8s

Created

about 2 years ago

Input

eta: 0
prompt: underwater++ world
max_width: 512
scheduler: DDIM
guess_mode
max_height: 512
num_outputs: 1
lineart_image: 955ad4a4680988283115264b5b45c211.jpg
guidance_scale: 7
negative_prompt: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
consistency_decoder
num_inference_steps: 10
disable_safety_check
tile_conditioning_scale: 1
depth_conditioning_scale: 1
lineart_conditioning_scale: 1
scribble_conditioning_scale: 1
brightness_conditioning_scale: 1
inpainting_conditioning_scale: 1

{
  "eta": 0,
  "prompt": "underwater++ world",
  "max_width": 512,
  "scheduler": "DDIM",
  "guess_mode": false,
  "max_height": 512,
  "num_outputs": 1,
  "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
  "guidance_scale": 7,
  "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "consistency_decoder": true,
  "num_inference_steps": 10,
  "disable_safety_check": true,
  "tile_conditioning_scale": 1,
  "depth_conditioning_scale": 1,
  "lineart_conditioning_scale": 1,
  "scribble_conditioning_scale": 1,
  "brightness_conditioning_scale": 1,
  "inpainting_conditioning_scale": 1
}

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 usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:a2d18c9c28b60d546c2e3ee2abab2196525d9ed70c74469e2c0efb39b097926d",
  {
    input: {
      eta: 0,
      prompt: "underwater++ world",
      max_width: 512,
      scheduler: "DDIM",
      guess_mode: false,
      max_height: 512,
      num_outputs: 1,
      lineart_image: "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
      guidance_scale: 7,
      negative_prompt: "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      consistency_decoder: true,
      num_inference_steps: 10,
      disable_safety_check: true,
      tile_conditioning_scale: 1,
      depth_conditioning_scale: 1,
      lineart_conditioning_scale: 1,
      scribble_conditioning_scale: 1,
      brightness_conditioning_scale: 1,
      inpainting_conditioning_scale: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:a2d18c9c28b60d546c2e3ee2abab2196525d9ed70c74469e2c0efb39b097926d",
    input={
        "eta": 0,
        "prompt": "underwater++ world",
        "max_width": 512,
        "scheduler": "DDIM",
        "guess_mode": False,
        "max_height": 512,
        "num_outputs": 1,
        "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
        "guidance_scale": 7,
        "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "consistency_decoder": True,
        "num_inference_steps": 10,
        "disable_safety_check": True,
        "tile_conditioning_scale": 1,
        "depth_conditioning_scale": 1,
        "lineart_conditioning_scale": 1,
        "scribble_conditioning_scale": 1,
        "brightness_conditioning_scale": 1,
        "inpainting_conditioning_scale": 1
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "usamaehsan/multi-controlnet-x-consistency-decoder-x-realestic-vision-v5:a2d18c9c28b60d546c2e3ee2abab2196525d9ed70c74469e2c0efb39b097926d",
    "input": {
      "eta": 0,
      "prompt": "underwater++ world",
      "max_width": 512,
      "scheduler": "DDIM",
      "guess_mode": false,
      "max_height": 512,
      "num_outputs": 1,
      "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
      "guidance_scale": 7,
      "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "consistency_decoder": true,
      "num_inference_steps": 10,
      "disable_safety_check": true,
      "tile_conditioning_scale": 1,
      "depth_conditioning_scale": 1,
      "lineart_conditioning_scale": 1,
      "scribble_conditioning_scale": 1,
      "brightness_conditioning_scale": 1,
      "inpainting_conditioning_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

seed-14308.png

{
  "completed_at": "2023-11-11T21:14:08.507534Z",
  "created_at": "2023-11-11T21:14:05.678884Z",
  "data_removed": false,
  "error": null,
  "id": "7q2acqdb3fd4hdjuutgvkk5aci",
  "input": {
    "eta": 0,
    "prompt": "underwater++ world",
    "max_width": 512,
    "scheduler": "DDIM",
    "guess_mode": false,
    "max_height": 512,
    "num_outputs": 1,
    "lineart_image": "https://replicate.delivery/pbxt/Jqzz9g4kPNdw0IyCqEGIXBHCr33Ai9agnbnZGdNVUUKoJqt3/955ad4a4680988283115264b5b45c211.jpg",
    "guidance_scale": 7,
    "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "consistency_decoder": true,
    "num_inference_steps": 10,
    "disable_safety_check": true,
    "tile_conditioning_scale": 1,
    "depth_conditioning_scale": 1,
    "lineart_conditioning_scale": 1,
    "scribble_conditioning_scale": 1,
    "brightness_conditioning_scale": 1,
    "inpainting_conditioning_scale": 1
  },
  "logs": "You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .\nUsing seed: 14308\n  0%|          | 0/10 [00:00<?, ?it/s]\n 30%|███       | 3/10 [00:00<00:00, 20.53it/s]\n 60%|██████    | 6/10 [00:00<00:00, 20.91it/s]\n 90%|█████████ | 9/10 [00:00<00:00, 21.03it/s]\n100%|██████████| 10/10 [00:00<00:00, 20.97it/s]\nRunning consistency decoder...\nConsistency decoder took 0.5379188060760498 seconds",
  "metrics": {
    "predict_time": 2.849712,
    "total_time": 2.82865
  },
  "output": [
    "https://replicate.delivery/pbxt/DpGJbw07XLYNL1c7cLq4Ls42ygGV8Sb4WfKedt7u2lefJodHB/seed-14308.png"
  ],
  "started_at": "2023-11-11T21:14:05.657822Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/7q2acqdb3fd4hdjuutgvkk5aci",
    "cancel": "https://api.replicate.com/v1/predictions/7q2acqdb3fd4hdjuutgvkk5aci/cancel"
  },
  "version": "a2d18c9c28b60d546c2e3ee2abab2196525d9ed70c74469e2c0efb39b097926d"
}

Generated in

2.9 seconds

Tweak it Iterate in playground Share Report

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (nixvsb3byk2c73cm6hq32v4boq)

Logs (sdezdcdbquw6b4wuwr5dso26eq)

Logs (tczw673btnldc2wz4rbqwkrf6i)

Logs (7q2acqdb3fd4hdjuutgvkk5aci)