zenaivn/dreambooth-inference | Run with an API on Replicate

zenaivn / dreambooth-inference

Cold

Public
3.1K runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

model_replicate_link

string

Shift + Return to add a new line

(Optional) Enter your model replicate link.

slider_lora_link

string

Shift + Return to add a new line

(Optional) if you want to use slider mode , enter your slider lora replicate link.

prompt

string

Shift + Return to add a new line

a professional photo portrait of ohwx womana professional photo portrait of ohwx woman

Input prompt

Default: "a professional photo portrait of ohwx woman"

negative_prompt

string

Shift + Return to add a new line

nude, old, wrinkles, mole, blemish, scar, cg, 3dnude, old, wrinkles, mole, blemish, scar, cg, 3d

Specify things to not see in the output

Default: "nude, old, wrinkles, mole, blemish, scar, cg, 3d"

weight_prompting

boolean

Choose if you want to use weight_prompting.

Default: true

only_super_resolution

boolean

Choose if you only want to upscale the image (this will do SUPIR and CCSR upscale).

Default: false

only_super_resolution_images

string

Shift + Return to add a new line

Enter your str of input images for only upscale the image.

Default: ""

only_inpainting

boolean

Choose if you only want to inpainting the image.

Default: false

only_inpainting_images

string

Shift + Return to add a new line

Enter your str of input images for only inpainting the image.

Default: ""

upscale_for_inpainting

boolean

Choose if you only want to upscale image

Default: true

is_inpainting_n2h

boolean

Choose if the mask close to face

Default: false

single_faceswap

boolean

Choose if you want to single-swap and enhance face.

Default: false

single_faceswap_ipadapter

boolean

Choose if you want to faceswap using ipadapter

Default: true

multi_faceswap

boolean

Choose if you want to multi-swap and enhance face.

Default: false

codeformer_enhancement

boolean

Use Codeformer restoration for enhance face.

Default: false

gfpgan_enhancement

boolean

Use GFPGAN restoration for enhance face.

Default: false

super_resolution_realesrgan_2x

boolean

Choose if you want to upscale the image using RealESRGAN

Default: false

super_resolution_realesrgan_4x

boolean

Choose if you want to upscale the image using RealESRGAN 4x

Default: true

super_resolution_clarity

boolean

Choose if you want to upscale the image using CLARITY

Default: false

super_resolution_supir_ccsr

boolean

Choose if you want to upscale the image using SUPIR and CCSR

Default: false

hiresfix

boolean

Choose if you want to hiresfix the image

Default: true

inpaint_face

boolean

Choose if you want to inpaint face

Default: true

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 640

num_outputs

integer

(minimum: 1, maximum: 30)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 35

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=zenaivn/dreambooth-inference

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 zenaivn/dreambooth-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zenaivn/dreambooth-inference:3c1a91b8890160b64d7868228df65ceb69ec4f874c311e81f8c6259bb46ea8b6",
  {
    input: {
      width: 512,
      height: 640,
      prompt: "a professional photo portrait of ohwx woman",
      hiresfix: true,
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      inpaint_face: true,
      guidance_scale: 7.5,
      multi_faceswap: false,
      negative_prompt: "nude, old, wrinkles, mole, blemish, scar, cg, 3d",
      only_inpainting: false,
      single_faceswap: false,
      weight_prompting: true,
      is_inpainting_n2h: false,
      gfpgan_enhancement: false,
      num_inference_steps: 35,
      only_super_resolution: false,
      codeformer_enhancement: false,
      only_inpainting_images: "",
      upscale_for_inpainting: true,
      super_resolution_clarity: false,
      single_faceswap_ipadapter: true,
      super_resolution_supir_ccsr: false,
      only_super_resolution_images: "",
      super_resolution_realesrgan_2x: false,
      super_resolution_realesrgan_4x: 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 zenaivn/dreambooth-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zenaivn/dreambooth-inference:3c1a91b8890160b64d7868228df65ceb69ec4f874c311e81f8c6259bb46ea8b6",
    input={
        "width": 512,
        "height": 640,
        "prompt": "a professional photo portrait of ohwx woman",
        "hiresfix": True,
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "inpaint_face": True,
        "guidance_scale": 7.5,
        "multi_faceswap": False,
        "negative_prompt": "nude, old, wrinkles, mole, blemish, scar, cg, 3d",
        "only_inpainting": False,
        "single_faceswap": False,
        "weight_prompting": True,
        "is_inpainting_n2h": False,
        "gfpgan_enhancement": False,
        "num_inference_steps": 35,
        "only_super_resolution": False,
        "codeformer_enhancement": False,
        "only_inpainting_images": "",
        "upscale_for_inpainting": True,
        "super_resolution_clarity": False,
        "single_faceswap_ipadapter": True,
        "super_resolution_supir_ccsr": False,
        "only_super_resolution_images": "",
        "super_resolution_realesrgan_2x": False,
        "super_resolution_realesrgan_4x": True
    }
)

# 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.

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Run zenaivn/dreambooth-inference 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": "zenaivn/dreambooth-inference:3c1a91b8890160b64d7868228df65ceb69ec4f874c311e81f8c6259bb46ea8b6",
    "input": {
      "width": 512,
      "height": 640,
      "prompt": "a professional photo portrait of ohwx woman",
      "hiresfix": true,
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "inpaint_face": true,
      "guidance_scale": 7.5,
      "multi_faceswap": false,
      "negative_prompt": "nude, old, wrinkles, mole, blemish, scar, cg, 3d",
      "only_inpainting": false,
      "single_faceswap": false,
      "weight_prompting": true,
      "is_inpainting_n2h": false,
      "gfpgan_enhancement": false,
      "num_inference_steps": 35,
      "only_super_resolution": false,
      "codeformer_enhancement": false,
      "only_inpainting_images": "",
      "upscale_for_inpainting": true,
      "super_resolution_clarity": false,
      "single_faceswap_ipadapter": true,
      "super_resolution_supir_ccsr": false,
      "only_super_resolution_images": "",
      "super_resolution_realesrgan_2x": false,
      "super_resolution_realesrgan_4x": 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 A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.