prompthunt/model_cf | Run with an API on Replicate

prompthunt / model_cf

(Updated 1 year, 6 months ago)

Cold

Public
303 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

weights

string

Shift + Return to add a new line

Weights url

control_image

file

Optional Image to use for guidance based on posenet

pose_image

file

Direct Pose image to use for guidance based on posenet, if available, ignores control_image

image

file

Optional Image to use for img2img guidance

mask

file

Optional Mask to use for legacy inpainting

prompt

string

Shift + Return to add a new line

Input prompt

Default: "photo of cjw person"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output. Supported embeddings: realisticvision-negative-embedding, cyberrealistic-neg, EasyNegative, FastNegativeV2, negative-hand, BadDream, UnrealisticDream, badhandv4

Default: ""

width

integer

Width of output image

Default: 512

height

integer

Height of output image

Default: 512

num_outputs

integer

(minimum: 1, maximum: 40)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

scheduler

string

Choose a scheduler.

Default: "DPM++SDEKarras"

seed

integer

Random seed. Leave blank to randomize the seed

source_image

file

Source image for face swap

show_debug_images

boolean

Show debug images

Default: false

upscale_final_size

integer

Upscale final size multiplier

Default: 4

upscale_fidelity

number

Upscale codeformer fidelity

Default: 0.7

upscale_background_enhance

boolean

Upscale background enhance

Default: true

upscale_face_upsample

boolean

Upscale face upsample

Default: true

use_new_vae

boolean

Use new vae

Default: false

second_pass_strength

number

Second pass strength

Default: 0.8

second_pass_guidance_scale

number

Second pass guidance scale

Default: 3

second_pass_steps

integer

Second pass steps

Default: 50

prompt_2

string

Shift + Return to add a new line

Input prompt

prompt_3

string

Shift + Return to add a new line

Input prompt

prompt_4

string

Shift + Return to add a new line

Input prompt

pose_image_2

file

Direct Pose image to use for guidance based on posenet, if available, ignores control_image

pose_image_3

file

Direct Pose image to use for guidance based on posenet, if available, ignores control_image

pose_image_4

file

Direct Pose image to use for guidance based on posenet, if available, ignores control_image

image_2

file

Optional Image to use for img2img guidance

image_3

file

Optional Image to use for img2img guidance

image_4

file

Optional Image to use for img2img guidance

prompt_strength_2

number

(minimum: 0, maximum: 1)

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

prompt_strength_3

number

(minimum: 0, maximum: 1)

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

prompt_strength_4

number

(minimum: 0, maximum: 1)

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

source_image_2

file

Source image for face swap

source_image_3

file

Source image for face swap

source_image_4

file

Source image for face swap

disable_cn_second_pass

boolean

Disable controlnet second pass

Default: false

use_tile

boolean

Use tile

Default: false

cf_acc_id

string

Shift + Return to add a new line

Cloudflare account ID

cf_api_key

string

Shift + Return to add a new line

Cloudflare API key

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

npx create-replicate --model=prompthunt/model_cf

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run prompthunt/model_cf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "prompthunt/model_cf:52b23475e5b79ce5db0275dc006aa8441c3cfaf07f4c82c433555dddc878c512",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "photo of cjw person",
      use_tile: false,
      scheduler: "DPM++SDEKarras",
      num_outputs: 1,
      use_new_vae: false,
      guidance_scale: 7.5,
      negative_prompt: "",
      prompt_strength: 0.8,
      upscale_fidelity: 0.7,
      prompt_strength_2: 0.8,
      prompt_strength_3: 0.8,
      prompt_strength_4: 0.8,
      second_pass_steps: 50,
      show_debug_images: false,
      upscale_final_size: 4,
      num_inference_steps: 50,
      second_pass_strength: 0.8,
      upscale_face_upsample: true,
      disable_cn_second_pass: false,
      second_pass_guidance_scale: 3,
      upscale_background_enhance: true
    }
  }
);

// 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 prompthunt/model_cf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prompthunt/model_cf:52b23475e5b79ce5db0275dc006aa8441c3cfaf07f4c82c433555dddc878c512",
    input={
        "width": 512,
        "height": 512,
        "prompt": "photo of cjw person",
        "use_tile": False,
        "scheduler": "DPM++SDEKarras",
        "num_outputs": 1,
        "use_new_vae": False,
        "guidance_scale": 7.5,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "upscale_fidelity": 0.7,
        "prompt_strength_2": 0.8,
        "prompt_strength_3": 0.8,
        "prompt_strength_4": 0.8,
        "second_pass_steps": 50,
        "show_debug_images": False,
        "upscale_final_size": 4,
        "num_inference_steps": 50,
        "second_pass_strength": 0.8,
        "upscale_face_upsample": True,
        "disable_cn_second_pass": False,
        "second_pass_guidance_scale": 3,
        "upscale_background_enhance": True
    }
)
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 prompthunt/model_cf 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": "prompthunt/model_cf:52b23475e5b79ce5db0275dc006aa8441c3cfaf07f4c82c433555dddc878c512",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "photo of cjw person",
      "use_tile": false,
      "scheduler": "DPM++SDEKarras",
      "num_outputs": 1,
      "use_new_vae": false,
      "guidance_scale": 7.5,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "upscale_fidelity": 0.7,
      "prompt_strength_2": 0.8,
      "prompt_strength_3": 0.8,
      "prompt_strength_4": 0.8,
      "second_pass_steps": 50,
      "show_debug_images": false,
      "upscale_final_size": 4,
      "num_inference_steps": 50,
      "second_pass_strength": 0.8,
      "upscale_face_upsample": true,
      "disable_cn_second_pass": false,
      "second_pass_guidance_scale": 3,
      "upscale_background_enhance": true
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.