underthestar2021/homo_fidelis-public | Run with an API on Replicate

underthestar2021 / homo_fidelis-public

(Updated 1 year, 6 months ago)

Cold

Public
37.2K runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

face_image

file

Input face image

remark

string

Shift + Return to add a new line

备注项，随便填

prompt

string

Shift + Return to add a new line

a photo of an astronaut riding a horse on marsa photo of an astronaut riding a horse on mars

Input prompt

Default: "a photo of an astronaut riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

prompt_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.7

pipe_type

string

画图类型，文生图还是图生图。不可以选空

Default: "txt2img"

clip_skip

integer

(minimum: 1)

Default: 2

seed

integer

Random seed. Leave blank to randomize the seed

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 26

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

target_width

integer

(minimum: 1, maximum: 1024)

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

Default: 512

target_height

integer

(minimum: 1, maximum: 1024)

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

Default: 720

scheduler

string

Choose a scheduler.

Default: "DPM++ SDE Karras"

controlnet_enable

boolean

是否启用Controlnet

Default: true

controlnet_type

string

An enumeration.

Default: "canny"

controlnet_conditioning_scale

number

(minimum: 0, maximum: 2)

Control Weight

Default: 1

canny_low_threshold

integer

(minimum: 1, maximum: 255)

Canny line detection low threshold

Default: 100

canny_high_threshold

integer

(minimum: 1, maximum: 255)

Canny line detection high threshold

Default: 200

control_guidance_start

number

(minimum: 0, maximum: 1)

The percentage of total steps at which the controlnet starts applying

Default: 0

control_guidance_end

number

(minimum: 0, maximum: 1)

The percentage of total steps at which the controlnet stops applying

Default: 1

lora_model

string

An enumeration.

lora_model_extra_url

string

Shift + Return to add a new line

测试lora时使用；lora模型的下载地址，如果填写会复盖掉lora_model参数

cross_attention_scale

number

lora权重，区间0-1. A scale value of 0 is the same as not using your LoRA weights and you’re only using the base model weights, and a scale value of 1 means you’re only using the fully fine-tuned LoRA weights.

Default: 0.8

swap_face_enable

boolean

是否使用swap_face(roop的换脸功能),默认True

Default: true

restore_face_enable

boolean

是否使用restore_face,默认True

Default: true

restore_face_upscale

integer

(minimum: 1, maximum: 4)

Restore face upscaling

Default: 1

restore_face_upsample

boolean

Restore face upsampling

Default: true

restore_face_background_enhance

boolean

Restore face background enhance

Default: true

codeformer_fidelity

number

(minimum: 0, maximum: 1)

Codeformer fidelity

Default: 0.7

face_editor_enable

boolean

是否使用face editor,默认False

Default: false

face_editor_strength1

number

(minimum: 0.1, maximum: 0.8)

Step 0.05, face editor, denoising strength for face images, sdwebui:(3) Recreate the Faces

Default: 0.4

face_editor_strength2

number

(minimum: 0, maximum: 1)

Step 0.05, face editor, denoising strength for the entire image, sdwebui:(5) Blend the entire image

Default: 0.05

face_editor_mask_size

integer

Face editor mask size

Default: 6

face_editor_mask_blur

integer

Face editor mask blur

Default: 12

face_editor_confidence

number

(minimum: 0.7, maximum: 1)

Confidence threshold for face detection. Set a lower value if you want to detect more faces.

Default: 0.97

resize_mode

string

fill - The image is resized to fill the given dimension. cover - The image keeps its aspect ratio and fills the given dimension. The image will be clipped to fit. crop - The image keeps its aspect ratio and scales to the target size.

Default: "fill"

uid

string

Shift + Return to add a new line

Unique identifier for this run. Will be used in callback.

task_id

string

Shift + Return to add a new line

Task ID for this run. Will be used in callback.

firebase_api_version

integer

api version

Default: 4

on_process_callback

string

Shift + Return to add a new line

Process callback URL for this .

complete_callback

string

Shift + Return to add a new line

Complete callback URL for this run.

callback_steps

integer

(minimum: 1, maximum: 100)

Callback URL for this run.

Default: 4

ai_random

string

Shift + Return to add a new line

random seed

Default: "ai_random"

show_system_info

boolean

Show system info

Default: false

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

npx create-replicate --model=underthestar2021/homo_fidelis-public

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 underthestar2021/homo_fidelis-public using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "underthestar2021/homo_fidelis-public:b558b3603914a5c2a12bc5431e8d84e564a301ba78a38f99683ea557e505d6d2",
  {
    input: {
      prompt: "a photo of an astronaut riding a horse on mars",
      ai_random: "ai_random",
      clip_skip: 2,
      pipe_type: "txt2img",
      scheduler: "DPM++ SDE Karras",
      lora_model: "empty",
      num_outputs: 1,
      resize_mode: "fill",
      target_width: 512,
      target_height: 720,
      callback_steps: 4,
      guidance_scale: 7.5,
      controlnet_type: "canny",
      prompt_strength: 0.7,
      show_system_info: false,
      swap_face_enable: true,
      controlnet_enable: true,
      face_editor_enable: false,
      canny_low_threshold: 100,
      codeformer_fidelity: 0.7,
      num_inference_steps: 26,
      restore_face_enable: true,
      canny_high_threshold: 200,
      control_guidance_end: 1,
      firebase_api_version: 4,
      restore_face_upscale: 1,
      cross_attention_scale: 0.8,
      face_editor_mask_blur: 12,
      face_editor_mask_size: 6,
      face_editor_strength1: 0.4,
      face_editor_strength2: 0.05,
      restore_face_upsample: true,
      control_guidance_start: 0,
      face_editor_confidence: 0.97,
      controlnet_conditioning_scale: 1,
      restore_face_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 underthestar2021/homo_fidelis-public using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "underthestar2021/homo_fidelis-public:b558b3603914a5c2a12bc5431e8d84e564a301ba78a38f99683ea557e505d6d2",
    input={
        "prompt": "a photo of an astronaut riding a horse on mars",
        "ai_random": "ai_random",
        "clip_skip": 2,
        "pipe_type": "txt2img",
        "scheduler": "DPM++ SDE Karras",
        "lora_model": "empty",
        "num_outputs": 1,
        "resize_mode": "fill",
        "target_width": 512,
        "target_height": 720,
        "callback_steps": 4,
        "guidance_scale": 7.5,
        "controlnet_type": "canny",
        "prompt_strength": 0.7,
        "show_system_info": False,
        "swap_face_enable": True,
        "controlnet_enable": True,
        "face_editor_enable": False,
        "canny_low_threshold": 100,
        "codeformer_fidelity": 0.7,
        "num_inference_steps": 26,
        "restore_face_enable": True,
        "canny_high_threshold": 200,
        "control_guidance_end": 1,
        "firebase_api_version": 4,
        "restore_face_upscale": 1,
        "cross_attention_scale": 0.8,
        "face_editor_mask_blur": 12,
        "face_editor_mask_size": 6,
        "face_editor_strength1": 0.4,
        "face_editor_strength2": 0.05,
        "restore_face_upsample": True,
        "control_guidance_start": 0,
        "face_editor_confidence": 0.97,
        "controlnet_conditioning_scale": 1,
        "restore_face_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 underthestar2021/homo_fidelis-public 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": "underthestar2021/homo_fidelis-public:b558b3603914a5c2a12bc5431e8d84e564a301ba78a38f99683ea557e505d6d2",
    "input": {
      "prompt": "a photo of an astronaut riding a horse on mars",
      "ai_random": "ai_random",
      "clip_skip": 2,
      "pipe_type": "txt2img",
      "scheduler": "DPM++ SDE Karras",
      "lora_model": "empty",
      "num_outputs": 1,
      "resize_mode": "fill",
      "target_width": 512,
      "target_height": 720,
      "callback_steps": 4,
      "guidance_scale": 7.5,
      "controlnet_type": "canny",
      "prompt_strength": 0.7,
      "show_system_info": false,
      "swap_face_enable": true,
      "controlnet_enable": true,
      "face_editor_enable": false,
      "canny_low_threshold": 100,
      "codeformer_fidelity": 0.7,
      "num_inference_steps": 26,
      "restore_face_enable": true,
      "canny_high_threshold": 200,
      "control_guidance_end": 1,
      "firebase_api_version": 4,
      "restore_face_upscale": 1,
      "cross_attention_scale": 0.8,
      "face_editor_mask_blur": 12,
      "face_editor_mask_size": 6,
      "face_editor_strength1": 0.4,
      "face_editor_strength2": 0.05,
      "restore_face_upsample": true,
      "control_guidance_start": 0,
      "face_editor_confidence": 0.97,
      "controlnet_conditioning_scale": 1,
      "restore_face_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 costs approximately $0.026 to run on Replicate, or 38 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 27 seconds.

Readme

This model doesn't have a readme.