camenduru/comfyui-ipadapter-latentupscale:f4ed8ed0

Version

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

camenduru /comfyui-ipadapter-latentupscale:f4ed8ed0

Playground API

Input

red_part

*file

Preview

Red part

red_positive_prompt

string

Shift + Return to add a new line

anime of a young woman with a red jacketanime of a young woman with a red jacket

Default: "anime illustration of a young woman with a black jacket"

red_negative_prompt

string

Shift + Return to add a new line

Default: ""

red_threshold

number

Default: 0.15

red_image_weight

number

Default: 0.7

red_prompt_weight

number

Default: 1

green_part

*file

Preview

Green part

green_positive_prompt

string

Shift + Return to add a new line

Default: "illustration of a blond woman"

green_negative_prompt

string

Shift + Return to add a new line

Default: "anime"

green_threshold

number

Default: 0.15

green_image_weight

number

Default: 0.7

green_prompt_weight

number

Default: 1

black_part

*file

Preview

Black part

black_positive_prompt

string

Shift + Return to add a new line

close-up of two girlfriends inside a ship.close-up of two girlfriends inside a ship.

Default: "closeup of two girl friends shopping in a sci-fi space station"

black_negative_prompt

string

Shift + Return to add a new line

Default: "blurry, lowres, bad art, ill, distorted, malformed, horror"

black_threshold

number

Default: 0.15

black_image_weight

number

Default: 0.7

black_prompt_weight

number

Default: 1

color_mask

*file

Preview

Color Mask

seed

integer

Default: 543543

steps

integer

Default: 30

cfg

number

Default: 7

sampler_name

string

An enumeration.

Default: "dpmpp_2m"

scheduler

string

An enumeration.

Default: "karras"

width

integer

Default: 768

height

integer

Default: 512

image_denoise

number

Default: 1

latent_upscale

boolean

Latent Upscale

Default: false

latent_upscale_size

number

Default: 1.5

latent_upscale_denoise

number

Default: 0.55

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

npx create-replicate --model=camenduru/comfyui-ipadapter-latentupscale

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 camenduru/comfyui-ipadapter-latentupscale using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "camenduru/comfyui-ipadapter-latentupscale:f4ed8ed006c27bc298d827a5de1943ca829e5eb4ed2c98d83670c3dfbf9292f0",
  {
    input: {
      cfg: 7,
      seed: 1,
      steps: 30,
      width: 768,
      height: 512,
      red_part: "https://replicate.delivery/pbxt/KnHfMGDCeId745aet6XgL8CJz1qSdmXfYR08uEvIpVVdmyRL/ip.png",
      scheduler: "karras",
      black_part: "https://replicate.delivery/pbxt/KnHfMUgxgdiQ1m8H1Xq82Xx30Up5kSsozWpawRgd6W0NIjqx/back1.png",
      color_mask: "https://replicate.delivery/pbxt/KnHfMziYJ1zzjMkQ0Ae9mUMXRcrxILcCx7pTwa9Mq3KrSeBD/color_mask.png",
      green_part: "https://replicate.delivery/pbxt/KnHfN2xxfEBSFURSNmXr9nByrm2eeXBcZ3fg1boIinDemZ9s/ip2.png",
      sampler_name: "dpmpp_2m",
      image_denoise: 1,
      red_threshold: 0.15,
      latent_upscale: true,
      black_threshold: 0.15,
      green_threshold: 0.15,
      red_image_weight: 0.7,
      red_prompt_weight: 1,
      black_image_weight: 0.7,
      green_image_weight: 0.7,
      black_prompt_weight: 1,
      green_prompt_weight: 1,
      latent_upscale_size: 1.5,
      red_negative_prompt: "",
      red_positive_prompt: "anime of a young woman with a red jacket",
      black_negative_prompt: "blurry, low-res, bad art",
      black_positive_prompt: "close-up of two girlfriends inside a ship.",
      green_negative_prompt: "anime",
      green_positive_prompt: "illustration of a blond woman",
      latent_upscale_denoise: 0.55
    }
  }
);

// 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

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 camenduru/comfyui-ipadapter-latentupscale using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "camenduru/comfyui-ipadapter-latentupscale:f4ed8ed006c27bc298d827a5de1943ca829e5eb4ed2c98d83670c3dfbf9292f0",
    input={
        "cfg": 7,
        "seed": 1,
        "steps": 30,
        "width": 768,
        "height": 512,
        "red_part": "https://replicate.delivery/pbxt/KnHfMGDCeId745aet6XgL8CJz1qSdmXfYR08uEvIpVVdmyRL/ip.png",
        "scheduler": "karras",
        "black_part": "https://replicate.delivery/pbxt/KnHfMUgxgdiQ1m8H1Xq82Xx30Up5kSsozWpawRgd6W0NIjqx/back1.png",
        "color_mask": "https://replicate.delivery/pbxt/KnHfMziYJ1zzjMkQ0Ae9mUMXRcrxILcCx7pTwa9Mq3KrSeBD/color_mask.png",
        "green_part": "https://replicate.delivery/pbxt/KnHfN2xxfEBSFURSNmXr9nByrm2eeXBcZ3fg1boIinDemZ9s/ip2.png",
        "sampler_name": "dpmpp_2m",
        "image_denoise": 1,
        "red_threshold": 0.15,
        "latent_upscale": True,
        "black_threshold": 0.15,
        "green_threshold": 0.15,
        "red_image_weight": 0.7,
        "red_prompt_weight": 1,
        "black_image_weight": 0.7,
        "green_image_weight": 0.7,
        "black_prompt_weight": 1,
        "green_prompt_weight": 1,
        "latent_upscale_size": 1.5,
        "red_negative_prompt": "",
        "red_positive_prompt": "anime of a young woman with a red jacket",
        "black_negative_prompt": "blurry, low-res, bad art",
        "black_positive_prompt": "close-up of two girlfriends inside a ship.",
        "green_negative_prompt": "anime",
        "green_positive_prompt": "illustration of a blond woman",
        "latent_upscale_denoise": 0.55
    }
)
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 camenduru/comfyui-ipadapter-latentupscale 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": "camenduru/comfyui-ipadapter-latentupscale:f4ed8ed006c27bc298d827a5de1943ca829e5eb4ed2c98d83670c3dfbf9292f0",
    "input": {
      "cfg": 7,
      "seed": 1,
      "steps": 30,
      "width": 768,
      "height": 512,
      "red_part": "https://replicate.delivery/pbxt/KnHfMGDCeId745aet6XgL8CJz1qSdmXfYR08uEvIpVVdmyRL/ip.png",
      "scheduler": "karras",
      "black_part": "https://replicate.delivery/pbxt/KnHfMUgxgdiQ1m8H1Xq82Xx30Up5kSsozWpawRgd6W0NIjqx/back1.png",
      "color_mask": "https://replicate.delivery/pbxt/KnHfMziYJ1zzjMkQ0Ae9mUMXRcrxILcCx7pTwa9Mq3KrSeBD/color_mask.png",
      "green_part": "https://replicate.delivery/pbxt/KnHfN2xxfEBSFURSNmXr9nByrm2eeXBcZ3fg1boIinDemZ9s/ip2.png",
      "sampler_name": "dpmpp_2m",
      "image_denoise": 1,
      "red_threshold": 0.15,
      "latent_upscale": true,
      "black_threshold": 0.15,
      "green_threshold": 0.15,
      "red_image_weight": 0.7,
      "red_prompt_weight": 1,
      "black_image_weight": 0.7,
      "green_image_weight": 0.7,
      "black_prompt_weight": 1,
      "green_prompt_weight": 1,
      "latent_upscale_size": 1.5,
      "red_negative_prompt": "",
      "red_positive_prompt": "anime of a young woman with a red jacket",
      "black_negative_prompt": "blurry, low-res, bad art",
      "black_positive_prompt": "close-up of two girlfriends inside a ship.",
      "green_negative_prompt": "anime",
      "green_positive_prompt": "illustration of a blond woman",
      "latent_upscale_denoise": 0.55
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-04-22T22:36:05.639331Z",
  "created_at": "2024-04-22T22:32:29.399000Z",
  "data_removed": false,
  "error": null,
  "id": "dyjczrvhtxrgm0cf0zr9frbwq8",
  "input": {
    "cfg": 7,
    "seed": 1,
    "steps": 30,
    "width": 768,
    "height": 512,
    "red_part": "https://replicate.delivery/pbxt/KnHfMGDCeId745aet6XgL8CJz1qSdmXfYR08uEvIpVVdmyRL/ip.png",
    "scheduler": "karras",
    "black_part": "https://replicate.delivery/pbxt/KnHfMUgxgdiQ1m8H1Xq82Xx30Up5kSsozWpawRgd6W0NIjqx/back1.png",
    "color_mask": "https://replicate.delivery/pbxt/KnHfMziYJ1zzjMkQ0Ae9mUMXRcrxILcCx7pTwa9Mq3KrSeBD/color_mask.png",
    "green_part": "https://replicate.delivery/pbxt/KnHfN2xxfEBSFURSNmXr9nByrm2eeXBcZ3fg1boIinDemZ9s/ip2.png",
    "sampler_name": "dpmpp_2m",
    "image_denoise": 1,
    "red_threshold": 0.15,
    "latent_upscale": true,
    "black_threshold": 0.15,
    "green_threshold": 0.15,
    "red_image_weight": 0.7,
    "red_prompt_weight": 1,
    "black_image_weight": 0.7,
    "green_image_weight": 0.7,
    "black_prompt_weight": 1,
    "green_prompt_weight": 1,
    "latent_upscale_size": 1.5,
    "red_negative_prompt": "",
    "red_positive_prompt": "anime of a young woman with a red jacket",
    "black_negative_prompt": "blurry, low-res, bad art",
    "black_positive_prompt": "close-up of two girlfriends inside a ship.",
    "green_negative_prompt": "anime",
    "green_positive_prompt": "illustration of a blond woman",
    "latent_upscale_denoise": 0.55
  },
  "logs": "Requested to load SD1ClipModel\nLoading 1 new model\nRequested to load CLIPVisionModelProjection\nLoading 1 new model\nRequested to load BaseModel\nLoading 1 new model\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:10,  2.83it/s]\n  7%|▋         | 2/30 [00:00<00:06,  4.05it/s]\n 10%|█         | 3/30 [00:00<00:05,  4.71it/s]\n 13%|█▎        | 4/30 [00:00<00:05,  5.09it/s]\n 17%|█▋        | 5/30 [00:01<00:04,  5.33it/s]\n 20%|██        | 6/30 [00:01<00:04,  5.48it/s]\n 23%|██▎       | 7/30 [00:01<00:04,  5.55it/s]\n 27%|██▋       | 8/30 [00:01<00:03,  5.61it/s]\n 30%|███       | 9/30 [00:01<00:03,  5.67it/s]\n 33%|███▎      | 10/30 [00:01<00:03,  5.71it/s]\n 37%|███▋      | 11/30 [00:02<00:03,  5.73it/s]\n 40%|████      | 12/30 [00:02<00:03,  5.75it/s]\n 43%|████▎     | 13/30 [00:02<00:02,  5.77it/s]\n 47%|████▋     | 14/30 [00:02<00:02,  5.77it/s]\n 50%|█████     | 15/30 [00:02<00:02,  5.78it/s]\n 53%|█████▎    | 16/30 [00:02<00:02,  5.78it/s]\n 57%|█████▋    | 17/30 [00:03<00:02,  5.80it/s]\n 60%|██████    | 18/30 [00:03<00:02,  5.80it/s]\n 63%|██████▎   | 19/30 [00:03<00:01,  5.79it/s]\n 67%|██████▋   | 20/30 [00:03<00:01,  5.80it/s]\n 70%|███████   | 21/30 [00:03<00:01,  5.79it/s]\n 73%|███████▎  | 22/30 [00:03<00:01,  5.79it/s]\n 77%|███████▋  | 23/30 [00:04<00:01,  5.79it/s]\n 80%|████████  | 24/30 [00:04<00:01,  5.78it/s]\n 83%|████████▎ | 25/30 [00:04<00:00,  5.79it/s]\n 87%|████████▋ | 26/30 [00:04<00:00,  5.78it/s]\n 90%|█████████ | 27/30 [00:04<00:00,  5.77it/s]\n 93%|█████████▎| 28/30 [00:05<00:00,  5.78it/s]\n 97%|█████████▋| 29/30 [00:05<00:00,  5.78it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.77it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.59it/s]\nRequested to load AutoencoderKL\nLoading 1 new model\n/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/cuda/memory.py:440: FutureWarning: torch.cuda.memory_cached has been renamed to torch.cuda.memory_reserved\nwarnings.warn(\n5154799616\n3946840064\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:11,  2.47it/s]\n  7%|▋         | 2/30 [00:00<00:11,  2.48it/s]\n 10%|█         | 3/30 [00:01<00:10,  2.49it/s]\n 13%|█▎        | 4/30 [00:01<00:10,  2.50it/s]\n 17%|█▋        | 5/30 [00:02<00:10,  2.50it/s]\n 20%|██        | 6/30 [00:02<00:09,  2.50it/s]\n 23%|██▎       | 7/30 [00:02<00:09,  2.50it/s]\n 27%|██▋       | 8/30 [00:03<00:08,  2.50it/s]\n 30%|███       | 9/30 [00:03<00:08,  2.50it/s]\n 33%|███▎      | 10/30 [00:04<00:07,  2.50it/s]\n 37%|███▋      | 11/30 [00:04<00:07,  2.50it/s]\n 40%|████      | 12/30 [00:04<00:07,  2.50it/s]\n 43%|████▎     | 13/30 [00:05<00:06,  2.50it/s]\n 47%|████▋     | 14/30 [00:05<00:06,  2.50it/s]\n 50%|█████     | 15/30 [00:06<00:05,  2.50it/s]\n 53%|█████▎    | 16/30 [00:06<00:05,  2.50it/s]\n 57%|█████▋    | 17/30 [00:06<00:05,  2.50it/s]\n 60%|██████    | 18/30 [00:07<00:04,  2.50it/s]\n 63%|██████▎   | 19/30 [00:07<00:04,  2.50it/s]\n 67%|██████▋   | 20/30 [00:08<00:04,  2.50it/s]\n 70%|███████   | 21/30 [00:08<00:03,  2.50it/s]\n 73%|███████▎  | 22/30 [00:08<00:03,  2.49it/s]\n 77%|███████▋  | 23/30 [00:09<00:02,  2.49it/s]\n 80%|████████  | 24/30 [00:09<00:02,  2.49it/s]\n 83%|████████▎ | 25/30 [00:10<00:02,  2.49it/s]\n 87%|████████▋ | 26/30 [00:10<00:01,  2.49it/s]\n 90%|█████████ | 27/30 [00:10<00:01,  2.49it/s]\n 93%|█████████▎| 28/30 [00:11<00:00,  2.49it/s]\n 97%|█████████▋| 29/30 [00:11<00:00,  2.49it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.49it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.50it/s]\n6037700608\n4339007488",
  "metrics": {
    "predict_time": 32.044086,
    "total_time": 216.240331
  },
  "output": [
    "https://replicate.delivery/pbxt/cSefZDG4y6qZm01lurTLBafZhEcujYBiWuxl3TqYm7tdCTalA/final_image.png",
    "https://replicate.delivery/pbxt/VgY5NgVT0yYsBteaT3PwFyvreWn5X3BKDY8tozGeXjtqCTalA/final_up_image.png"
  ],
  "started_at": "2024-04-22T22:35:33.595245Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/dyjczrvhtxrgm0cf0zr9frbwq8",
    "cancel": "https://api.replicate.com/v1/predictions/dyjczrvhtxrgm0cf0zr9frbwq8/cancel"
  },
  "version": "f4ed8ed006c27bc298d827a5de1943ca829e5eb4ed2c98d83670c3dfbf9292f0"
}

Generated in

32.0 seconds

Tweak it ShareReport

Requested to load SD1ClipModel
Loading 1 new model
Requested to load CLIPVisionModelProjection
Loading 1 new model
Requested to load BaseModel
Loading 1 new model
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:10,  2.83it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.05it/s]
 10%|█         | 3/30 [00:00<00:05,  4.71it/s]
 13%|█▎        | 4/30 [00:00<00:05,  5.09it/s]
 17%|█▋        | 5/30 [00:01<00:04,  5.33it/s]
 20%|██        | 6/30 [00:01<00:04,  5.48it/s]
 23%|██▎       | 7/30 [00:01<00:04,  5.55it/s]
 27%|██▋       | 8/30 [00:01<00:03,  5.61it/s]
 30%|███       | 9/30 [00:01<00:03,  5.67it/s]
 33%|███▎      | 10/30 [00:01<00:03,  5.71it/s]
 37%|███▋      | 11/30 [00:02<00:03,  5.73it/s]
 40%|████      | 12/30 [00:02<00:03,  5.75it/s]
 43%|████▎     | 13/30 [00:02<00:02,  5.77it/s]
 47%|████▋     | 14/30 [00:02<00:02,  5.77it/s]
 50%|█████     | 15/30 [00:02<00:02,  5.78it/s]
 53%|█████▎    | 16/30 [00:02<00:02,  5.78it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  5.80it/s]
 60%|██████    | 18/30 [00:03<00:02,  5.80it/s]
 63%|██████▎   | 19/30 [00:03<00:01,  5.79it/s]
 67%|██████▋   | 20/30 [00:03<00:01,  5.80it/s]
 70%|███████   | 21/30 [00:03<00:01,  5.79it/s]
 73%|███████▎  | 22/30 [00:03<00:01,  5.79it/s]
 77%|███████▋  | 23/30 [00:04<00:01,  5.79it/s]
 80%|████████  | 24/30 [00:04<00:01,  5.78it/s]
 83%|████████▎ | 25/30 [00:04<00:00,  5.79it/s]
 87%|████████▋ | 26/30 [00:04<00:00,  5.78it/s]
 90%|█████████ | 27/30 [00:04<00:00,  5.77it/s]
 93%|█████████▎| 28/30 [00:05<00:00,  5.78it/s]
 97%|█████████▋| 29/30 [00:05<00:00,  5.78it/s]
100%|██████████| 30/30 [00:05<00:00,  5.77it/s]
100%|██████████| 30/30 [00:05<00:00,  5.59it/s]
Requested to load AutoencoderKL
Loading 1 new model
/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/cuda/memory.py:440: FutureWarning: torch.cuda.memory_cached has been renamed to torch.cuda.memory_reserved
warnings.warn(
5154799616
3946840064
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:11,  2.47it/s]
  7%|▋         | 2/30 [00:00<00:11,  2.48it/s]
 10%|█         | 3/30 [00:01<00:10,  2.49it/s]
 13%|█▎        | 4/30 [00:01<00:10,  2.50it/s]
 17%|█▋        | 5/30 [00:02<00:10,  2.50it/s]
 20%|██        | 6/30 [00:02<00:09,  2.50it/s]
 23%|██▎       | 7/30 [00:02<00:09,  2.50it/s]
 27%|██▋       | 8/30 [00:03<00:08,  2.50it/s]
 30%|███       | 9/30 [00:03<00:08,  2.50it/s]
 33%|███▎      | 10/30 [00:04<00:07,  2.50it/s]
 37%|███▋      | 11/30 [00:04<00:07,  2.50it/s]
 40%|████      | 12/30 [00:04<00:07,  2.50it/s]
 43%|████▎     | 13/30 [00:05<00:06,  2.50it/s]
 47%|████▋     | 14/30 [00:05<00:06,  2.50it/s]
 50%|█████     | 15/30 [00:06<00:05,  2.50it/s]
 53%|█████▎    | 16/30 [00:06<00:05,  2.50it/s]
 57%|█████▋    | 17/30 [00:06<00:05,  2.50it/s]
 60%|██████    | 18/30 [00:07<00:04,  2.50it/s]
 63%|██████▎   | 19/30 [00:07<00:04,  2.50it/s]
 67%|██████▋   | 20/30 [00:08<00:04,  2.50it/s]
 70%|███████   | 21/30 [00:08<00:03,  2.50it/s]
 73%|███████▎  | 22/30 [00:08<00:03,  2.49it/s]
 77%|███████▋  | 23/30 [00:09<00:02,  2.49it/s]
 80%|████████  | 24/30 [00:09<00:02,  2.49it/s]
 83%|████████▎ | 25/30 [00:10<00:02,  2.49it/s]
 87%|████████▋ | 26/30 [00:10<00:01,  2.49it/s]
 90%|█████████ | 27/30 [00:10<00:01,  2.49it/s]
 93%|█████████▎| 28/30 [00:11<00:00,  2.49it/s]
 97%|█████████▋| 29/30 [00:11<00:00,  2.49it/s]
100%|██████████| 30/30 [00:12<00:00,  2.49it/s]
100%|██████████| 30/30 [00:12<00:00,  2.50it/s]
6037700608
4339007488