prompthunt/kohya | Run with an API on Replicate

prompthunt / kohya

Cold

Public
55 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples Train README Versions

Input

prompt

string

Shift + Return to add a new line

a TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league stylea TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league style

Input prompt

Default: "a TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league style"

negative_prompt

string

Shift + Return to add a new line

plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurryplastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry

Input Negative Prompt

Default: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 25

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 9

inpaint_prompt

string

Shift + Return to add a new line

closeup of TOK man, natural skin, skin moles, 37 y o caucasiancloseup of TOK man, natural skin, skin moles, 37 y o caucasian

Input inpaint prompt

Default: "closeup of TOK man, natural skin, skin moles, 37 y o caucasian"

inpaint_negative_prompt

string

Shift + Return to add a new line

plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurryplastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry

Input inpaint negative prompt

Default: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

inpaint_num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps for inpainting

Default: 25

inpaint_guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance for inpainting

Default: 9

inpaint_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.35

upscale_by

number

(minimum: 1, maximum: 4)

Upscale by factor

Default: 1.5

upscale_prompt

string

Shift + Return to add a new line

closeup of TOK man, natural skin, skin moles, 37 y o caucasiancloseup of TOK man, natural skin, skin moles, 37 y o caucasian

Input inpaint prompt

Default: "closeup of TOK man, natural skin, skin moles, 37 y o caucasian"

upscale_negative_prompt

string

Shift + Return to add a new line

plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurryplastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry

Input inpaint negative prompt

Default: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

upscale_num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps for inpainting

Default: 25

upscale_guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance for inpainting

Default: 9

upscale_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.35

width

integer

Width of output image

Default: 768

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

mask_blur_amount

number

Amount to blur the inpaint mask by

Default: 8

seed

integer

Random seed. Leave blank to randomize the seed

Default: 1234

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.4

pose_image

file

pose_image

controlnet_conditioning_scale

number

(minimum: 0, maximum: 1)

controlnet_conditioning_scale

Default: 0.6

weights

string

Shift + Return to add a new line

https://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tarhttps://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tar

Replicate LoRA weights to use. Leave blank to use the default weights.

Default: "https://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tar"

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

npx create-replicate --model=prompthunt/kohya

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

const output = await replicate.run(
  "prompthunt/kohya:f5f1122a02e0260aada7e9c274ce1befab036b688304cb711456e191a6f054c7",
  {
    input: {
      seed: 1234,
      width: 768,
      height: 1024,
      prompt: "a TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league style",
      weights: "https://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tar",
      scheduler: "K_EULER",
      lora_scale: 0.4,
      upscale_by: 1.5,
      num_outputs: 1,
      guidance_scale: 9,
      inpaint_prompt: "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
      upscale_prompt: "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
      negative_prompt: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      prompt_strength: 0.8,
      inpaint_strength: 0.35,
      mask_blur_amount: 8,
      upscale_strength: 0.35,
      num_inference_steps: 25,
      inpaint_guidance_scale: 9,
      upscale_guidance_scale: 9,
      inpaint_negative_prompt: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      upscale_negative_prompt: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      inpaint_num_inference_steps: 25,
      upscale_num_inference_steps: 25,
      controlnet_conditioning_scale: 0.6
    }
  }
);

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

output = replicate.run(
    "prompthunt/kohya:f5f1122a02e0260aada7e9c274ce1befab036b688304cb711456e191a6f054c7",
    input={
        "seed": 1234,
        "width": 768,
        "height": 1024,
        "prompt": "a TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league style",
        "weights": "https://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tar",
        "scheduler": "K_EULER",
        "lora_scale": 0.4,
        "upscale_by": 1.5,
        "num_outputs": 1,
        "guidance_scale": 9,
        "inpaint_prompt": "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
        "upscale_prompt": "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
        "negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "prompt_strength": 0.8,
        "inpaint_strength": 0.35,
        "mask_blur_amount": 8,
        "upscale_strength": 0.35,
        "num_inference_steps": 25,
        "inpaint_guidance_scale": 9,
        "upscale_guidance_scale": 9,
        "inpaint_negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "upscale_negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "inpaint_num_inference_steps": 25,
        "upscale_num_inference_steps": 25,
        "controlnet_conditioning_scale": 0.6
    }
)
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/kohya 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/kohya:f5f1122a02e0260aada7e9c274ce1befab036b688304cb711456e191a6f054c7",
    "input": {
      "seed": 1234,
      "width": 768,
      "height": 1024,
      "prompt": "a TOK man in preppy style, old money aesthetic, posh style, elite school stlye, luxurious style, gossip girl neo-prep style, ralph lauren style, country club style, ivy league style",
      "weights": "https://replicate.delivery/pbxt/cv7B5U7T4G4kFN8eXIg7F8FRfbC54hIWyeizfNuH9lcBevtOC/trained_model.tar",
      "scheduler": "K_EULER",
      "lora_scale": 0.4,
      "upscale_by": 1.5,
      "num_outputs": 1,
      "guidance_scale": 9,
      "inpaint_prompt": "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
      "upscale_prompt": "closeup of TOK man, natural skin, skin moles, 37 y o caucasian",
      "negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "prompt_strength": 0.8,
      "inpaint_strength": 0.35,
      "mask_blur_amount": 8,
      "upscale_strength": 0.35,
      "num_inference_steps": 25,
      "inpaint_guidance_scale": 9,
      "upscale_guidance_scale": 9,
      "inpaint_negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "upscale_negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "inpaint_num_inference_steps": 25,
      "upscale_num_inference_steps": 25,
      "controlnet_conditioning_scale": 0.6
    }
  }' \
  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.