jschoormans/sdxl-inpainting-trainable:81be9435 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

jschoormans /sdxl-inpainting-trainable:81be9435

Playground API

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

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

npx create-replicate --model=jschoormans/sdxl-inpainting-trainable

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";

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

Run jschoormans/sdxl-inpainting-trainable using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jschoormans/sdxl-inpainting-trainable:81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "An astronaut riding a rainbow unicorn",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);
console.log(output);

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 jschoormans/sdxl-inpainting-trainable using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jschoormans/sdxl-inpainting-trainable:81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "An astronaut riding a rainbow unicorn",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
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 jschoormans/sdxl-inpainting-trainable 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": "81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "An astronaut riding a rainbow unicorn",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

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

Pull and run jschoormans/sdxl-inpainting-trainable using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/jschoormans/sdxl-inpainting-trainable@sha256:81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102 \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="An astronaut riding a rainbow unicorn"' \
  -i 'refine="no_refiner"' \
  -i 'scheduler="K_EULER"' \
  -i 'lora_scale=0.6' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'apply_watermark=true' \
  -i 'high_noise_frac=0.8' \
  -i 'negative_prompt=""' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

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

Pull and run jschoormans/sdxl-inpainting-trainable using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/jschoormans/sdxl-inpainting-trainable@sha256:81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "An astronaut riding a rainbow unicorn",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

Output

{
  "completed_at": "2023-09-10T18:57:28.560348Z",
  "created_at": "2023-09-10T18:54:42.800703Z",
  "data_removed": false,
  "error": null,
  "id": "yerj3ilbgqt3nvgshbu224uoxy",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "An astronaut riding a rainbow unicorn",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 57216\nPrompt: An astronaut riding a rainbow unicorn\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:34,  1.43it/s]\n  4%|▍         | 2/50 [00:00<00:19,  2.46it/s]\n  6%|▌         | 3/50 [00:01<00:14,  3.19it/s]\n  8%|▊         | 4/50 [00:01<00:12,  3.72it/s]\n 10%|█         | 5/50 [00:01<00:11,  4.08it/s]\n 12%|█▏        | 6/50 [00:01<00:10,  4.34it/s]\n 14%|█▍        | 7/50 [00:01<00:09,  4.52it/s]\n 16%|█▌        | 8/50 [00:02<00:09,  4.65it/s]\n 18%|█▊        | 9/50 [00:02<00:08,  4.74it/s]\n 20%|██        | 10/50 [00:02<00:08,  4.80it/s]\n 22%|██▏       | 11/50 [00:02<00:08,  4.84it/s]\n 24%|██▍       | 12/50 [00:02<00:07,  4.88it/s]\n 26%|██▌       | 13/50 [00:03<00:07,  4.90it/s]\n 28%|██▊       | 14/50 [00:03<00:07,  4.91it/s]\n 30%|███       | 15/50 [00:03<00:07,  4.92it/s]\n 32%|███▏      | 16/50 [00:03<00:06,  4.91it/s]\n 34%|███▍      | 17/50 [00:03<00:06,  4.92it/s]\n 36%|███▌      | 18/50 [00:04<00:06,  4.93it/s]\n 38%|███▊      | 19/50 [00:04<00:06,  4.94it/s]\n 40%|████      | 20/50 [00:04<00:06,  4.94it/s]\n 42%|████▏     | 21/50 [00:04<00:05,  4.93it/s]\n 44%|████▍     | 22/50 [00:04<00:05,  4.93it/s]\n 46%|████▌     | 23/50 [00:05<00:05,  4.93it/s]\n 48%|████▊     | 24/50 [00:05<00:05,  4.93it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.93it/s]\n 52%|█████▏    | 26/50 [00:05<00:04,  4.93it/s]\n 54%|█████▍    | 27/50 [00:05<00:04,  4.93it/s]\n 56%|█████▌    | 28/50 [00:06<00:04,  4.94it/s]\n 58%|█████▊    | 29/50 [00:06<00:04,  4.94it/s]\n 60%|██████    | 30/50 [00:06<00:04,  4.95it/s]\n 62%|██████▏   | 31/50 [00:06<00:03,  4.95it/s]\n 64%|██████▍   | 32/50 [00:06<00:03,  4.95it/s]\n 66%|██████▌   | 33/50 [00:07<00:03,  4.96it/s]\n 68%|██████▊   | 34/50 [00:07<00:03,  4.96it/s]\n 70%|███████   | 35/50 [00:07<00:03,  4.96it/s]\n 72%|███████▏  | 36/50 [00:07<00:02,  4.96it/s]\n 74%|███████▍  | 37/50 [00:07<00:02,  4.97it/s]\n 76%|███████▌  | 38/50 [00:08<00:02,  4.97it/s]\n 78%|███████▊  | 39/50 [00:08<00:02,  4.97it/s]\n 80%|████████  | 40/50 [00:08<00:02,  4.97it/s]\n 82%|████████▏ | 41/50 [00:08<00:01,  4.96it/s]\n 84%|████████▍ | 42/50 [00:08<00:01,  4.97it/s]\n 86%|████████▌ | 43/50 [00:09<00:01,  4.96it/s]\n 88%|████████▊ | 44/50 [00:09<00:01,  4.96it/s]\n 90%|█████████ | 45/50 [00:09<00:01,  4.95it/s]\n 92%|█████████▏| 46/50 [00:09<00:00,  4.95it/s]\n 94%|█████████▍| 47/50 [00:09<00:00,  4.96it/s]\n 96%|█████████▌| 48/50 [00:10<00:00,  4.96it/s]\n 98%|█████████▊| 49/50 [00:10<00:00,  4.97it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.97it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.72it/s]",
  "metrics": {
    "predict_time": 13.285031,
    "total_time": 165.759645
  },
  "output": [
    "https://replicate.delivery/pbxt/WweF1FitVuyQXCf6FwQD2xBaOeOqbdkKxcBLmnRbAUed5wLGB/out-0.png"
  ],
  "started_at": "2023-09-10T18:57:15.275317Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yerj3ilbgqt3nvgshbu224uoxy",
    "cancel": "https://api.replicate.com/v1/predictions/yerj3ilbgqt3nvgshbu224uoxy/cancel"
  },
  "version": "81be943507a7c0d2d62c56ebce166edeb0635798841e096a898d4b4a57a43102"
}

Generated in

13.3 seconds

Tweak itReport

Using seed: 57216
Prompt: An astronaut riding a rainbow unicorn
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:34,  1.43it/s]
  4%|▍         | 2/50 [00:00<00:19,  2.46it/s]
  6%|▌         | 3/50 [00:01<00:14,  3.19it/s]
  8%|▊         | 4/50 [00:01<00:12,  3.72it/s]
 10%|█         | 5/50 [00:01<00:11,  4.08it/s]
 12%|█▏        | 6/50 [00:01<00:10,  4.34it/s]
 14%|█▍        | 7/50 [00:01<00:09,  4.52it/s]
 16%|█▌        | 8/50 [00:02<00:09,  4.65it/s]
 18%|█▊        | 9/50 [00:02<00:08,  4.74it/s]
 20%|██        | 10/50 [00:02<00:08,  4.80it/s]
 22%|██▏       | 11/50 [00:02<00:08,  4.84it/s]
 24%|██▍       | 12/50 [00:02<00:07,  4.88it/s]
 26%|██▌       | 13/50 [00:03<00:07,  4.90it/s]
 28%|██▊       | 14/50 [00:03<00:07,  4.91it/s]
 30%|███       | 15/50 [00:03<00:07,  4.92it/s]
 32%|███▏      | 16/50 [00:03<00:06,  4.91it/s]
 34%|███▍      | 17/50 [00:03<00:06,  4.92it/s]
 36%|███▌      | 18/50 [00:04<00:06,  4.93it/s]
 38%|███▊      | 19/50 [00:04<00:06,  4.94it/s]
 40%|████      | 20/50 [00:04<00:06,  4.94it/s]
 42%|████▏     | 21/50 [00:04<00:05,  4.93it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.93it/s]
 46%|████▌     | 23/50 [00:05<00:05,  4.93it/s]
 48%|████▊     | 24/50 [00:05<00:05,  4.93it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.93it/s]
 52%|█████▏    | 26/50 [00:05<00:04,  4.93it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.93it/s]
 56%|█████▌    | 28/50 [00:06<00:04,  4.94it/s]
 58%|█████▊    | 29/50 [00:06<00:04,  4.94it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.95it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.95it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.95it/s]
 66%|██████▌   | 33/50 [00:07<00:03,  4.96it/s]
 68%|██████▊   | 34/50 [00:07<00:03,  4.96it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.96it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.96it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.97it/s]
 76%|███████▌  | 38/50 [00:08<00:02,  4.97it/s]
 78%|███████▊  | 39/50 [00:08<00:02,  4.97it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.97it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.96it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.97it/s]
 86%|████████▌ | 43/50 [00:09<00:01,  4.96it/s]
 88%|████████▊ | 44/50 [00:09<00:01,  4.96it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.95it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.95it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.96it/s]
 96%|█████████▌| 48/50 [00:10<00:00,  4.96it/s]
 98%|█████████▊| 49/50 [00:10<00:00,  4.97it/s]
100%|██████████| 50/50 [00:10<00:00,  4.97it/s]
100%|██████████| 50/50 [00:10<00:00,  4.72it/s]