fofr/sdxl-fresh-ink | Run with an API on Replicate

fofr / sdxl-fresh-ink

SDXL fine-tuned on photos of freshly inked tattoos

Warm

Public
106.1K runs
L40S
SDXL fine-tune

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 1024

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"

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 img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Default: false

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

npx create-replicate --model=fofr/sdxl-fresh-ink

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 fofr/sdxl-fresh-ink using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/sdxl-fresh-ink:8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A fresh ink TOK tattoo",
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.9,
      negative_prompt: "ugly, broken, distorted",
      prompt_strength: 0.8,
      num_inference_steps: 25
    }
  }
);

// 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 fofr/sdxl-fresh-ink using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/sdxl-fresh-ink:8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A fresh ink TOK tattoo",
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.9,
        "negative_prompt": "ugly, broken, distorted",
        "prompt_strength": 0.8,
        "num_inference_steps": 25
    }
)
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 fofr/sdxl-fresh-ink 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": "fofr/sdxl-fresh-ink:8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A fresh ink TOK tattoo",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.9,
      "negative_prompt": "ugly, broken, distorted",
      "prompt_strength": 0.8,
      "num_inference_steps": 25
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/fofr/sdxl-fresh-ink@sha256:8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943 \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A fresh ink TOK tattoo"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="K_EULER"' \
  -i 'lora_scale=0.6' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'apply_watermark=false' \
  -i 'high_noise_frac=0.9' \
  -i 'negative_prompt="ugly, broken, distorted"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=25'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-fresh-ink@sha256:8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A fresh ink TOK tattoo",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.9,
      "negative_prompt": "ugly, broken, distorted",
      "prompt_strength": 0.8,
      "num_inference_steps": 25
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-01-09T16:48:48.991666Z",
  "created_at": "2024-01-09T16:48:36.980298Z",
  "data_removed": false,
  "error": null,
  "id": "qxwo2ylbjcpcobsx5ouimg7x3a",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A fresh ink TOK tattoo",
    "refine": "expert_ensemble_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": false,
    "high_noise_frac": 0.9,
    "negative_prompt": "ugly, broken, distorted",
    "prompt_strength": 0.8,
    "num_inference_steps": 25
  },
  "logs": "Using seed: 33170\nEnsuring enough disk space...\nFree disk space: 2130453733376\nDownloading weights: https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar\n2024-01-09T16:48:40Z | INFO  | [ Initiating ] dest=/src/weights-cache/9f5b12ce3d673053 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar\n2024-01-09T16:48:41Z | INFO  | [ Complete ] dest=/src/weights-cache/9f5b12ce3d673053 size=\"186 MB\" total_elapsed=0.820s url=https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar\nb''\nDownloaded weights in 0.9461627006530762 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A fresh ink <s0><s1> tattoo\ntxt2img mode\n  0%|          | 0/18 [00:00<?, ?it/s]\n  6%|▌         | 1/18 [00:00<00:04,  3.72it/s]\n 11%|█         | 2/18 [00:00<00:04,  3.69it/s]\n 17%|█▋        | 3/18 [00:00<00:04,  3.69it/s]\n 22%|██▏       | 4/18 [00:01<00:03,  3.68it/s]\n 28%|██▊       | 5/18 [00:01<00:03,  3.69it/s]\n 33%|███▎      | 6/18 [00:01<00:03,  3.69it/s]\n 39%|███▉      | 7/18 [00:01<00:02,  3.68it/s]\n 44%|████▍     | 8/18 [00:02<00:02,  3.68it/s]\n 50%|█████     | 9/18 [00:02<00:02,  3.68it/s]\n 56%|█████▌    | 10/18 [00:02<00:02,  3.69it/s]\n 61%|██████    | 11/18 [00:02<00:01,  3.69it/s]\n 67%|██████▋   | 12/18 [00:03<00:01,  3.69it/s]\n 72%|███████▏  | 13/18 [00:03<00:01,  3.69it/s]\n 78%|███████▊  | 14/18 [00:03<00:01,  3.69it/s]\n 83%|████████▎ | 15/18 [00:04<00:00,  3.69it/s]\n 89%|████████▉ | 16/18 [00:04<00:00,  3.69it/s]\n 94%|█████████▍| 17/18 [00:04<00:00,  3.69it/s]\n100%|██████████| 18/18 [00:04<00:00,  3.69it/s]\n100%|██████████| 18/18 [00:04<00:00,  3.69it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  4.31it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  4.27it/s]\n100%|██████████| 3/3 [00:00<00:00,  4.27it/s]\n100%|██████████| 3/3 [00:00<00:00,  4.28it/s]",
  "metrics": {
    "predict_time": 8.706767,
    "total_time": 12.011368
  },
  "output": [
    "https://replicate.delivery/pbxt/KXrjXKjczHK6MxVIjgoCeJffm0uP5LlzEyPrHjwceeXDeqsiE/out-0.png"
  ],
  "started_at": "2024-01-09T16:48:40.284899Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/qxwo2ylbjcpcobsx5ouimg7x3a",
    "cancel": "https://api.replicate.com/v1/predictions/qxwo2ylbjcpcobsx5ouimg7x3a/cancel"
  },
  "version": "8515c238222fa529763ec99b4ba1fa9d32ab5d6ebc82b4281de99e4dbdcec943"
}

Generated in

8.7 seconds

Tweak itReport View full prediction

Using seed: 33170
Ensuring enough disk space...
Free disk space: 2130453733376
Downloading weights: https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar
2024-01-09T16:48:40Z | INFO  | [ Initiating ] dest=/src/weights-cache/9f5b12ce3d673053 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar
2024-01-09T16:48:41Z | INFO  | [ Complete ] dest=/src/weights-cache/9f5b12ce3d673053 size="186 MB" total_elapsed=0.820s url=https://replicate.delivery/pbxt/GueLVKd75jxiXKEAmKAIV0dSwa0f7aHMYIl0itvXuFlRekVkA/trained_model.tar
b''
Downloaded weights in 0.9461627006530762 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: A fresh ink <s0><s1> tattoo
txt2img mode
  0%|          | 0/18 [00:00<?, ?it/s]
  6%|▌         | 1/18 [00:00<00:04,  3.72it/s]
 11%|█         | 2/18 [00:00<00:04,  3.69it/s]
 17%|█▋        | 3/18 [00:00<00:04,  3.69it/s]
 22%|██▏       | 4/18 [00:01<00:03,  3.68it/s]
 28%|██▊       | 5/18 [00:01<00:03,  3.69it/s]
 33%|███▎      | 6/18 [00:01<00:03,  3.69it/s]
 39%|███▉      | 7/18 [00:01<00:02,  3.68it/s]
 44%|████▍     | 8/18 [00:02<00:02,  3.68it/s]
 50%|█████     | 9/18 [00:02<00:02,  3.68it/s]
 56%|█████▌    | 10/18 [00:02<00:02,  3.69it/s]
 61%|██████    | 11/18 [00:02<00:01,  3.69it/s]
 67%|██████▋   | 12/18 [00:03<00:01,  3.69it/s]
 72%|███████▏  | 13/18 [00:03<00:01,  3.69it/s]
 78%|███████▊  | 14/18 [00:03<00:01,  3.69it/s]
 83%|████████▎ | 15/18 [00:04<00:00,  3.69it/s]
 89%|████████▉ | 16/18 [00:04<00:00,  3.69it/s]
 94%|█████████▍| 17/18 [00:04<00:00,  3.69it/s]
100%|██████████| 18/18 [00:04<00:00,  3.69it/s]
100%|██████████| 18/18 [00:04<00:00,  3.69it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  4.31it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  4.27it/s]
100%|██████████| 3/3 [00:00<00:00,  4.27it/s]
100%|██████████| 3/3 [00:00<00:00,  4.28it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.013 to run on Replicate, or 76 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 14 seconds.

Readme

This model doesn't have a readme.