cjwbw/stable-diffusion-v2-inpainting – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

face of a ginger cat, high resolution, sitting on a park benchface of a ginger cat, high resolution, sitting on a park bench

Input prompt

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

image

*file

Preview

Inital image to generate variations of. Supproting images size with 512x512

mask

*file

Preview

Black and white image to use as mask for inpainting over the image provided. Black pixels are inpainted and white pixels are preserved

prompt_strength

number

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

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 8)

Number of images to output. Higher number of outputs may OOM.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

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=cjwbw/stable-diffusion-v2-inpainting

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 cjwbw/stable-diffusion-v2-inpainting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cjwbw/stable-diffusion-v2-inpainting:f9bb0632bfdceb83196e85521b9b55895f8ff3d1d3b487fd1973210c0eb30bec",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/HszfSoPGhMEvXf9Gf5gA564aMMyuki3TLSlQQmCepokDJy47/mask.png",
      image: "https://replicate.delivery/pbxt/HszfS11BnkFTWHKv6sa5kQgrGGcLk0r1ihgUVAZp2bQJ0Yq9/dog.png",
      prompt: "face of a ginger cat, high resolution, sitting on a park bench",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 cjwbw/stable-diffusion-v2-inpainting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/stable-diffusion-v2-inpainting:f9bb0632bfdceb83196e85521b9b55895f8ff3d1d3b487fd1973210c0eb30bec",
    input={
        "mask": "https://replicate.delivery/pbxt/HszfSoPGhMEvXf9Gf5gA564aMMyuki3TLSlQQmCepokDJy47/mask.png",
        "image": "https://replicate.delivery/pbxt/HszfS11BnkFTWHKv6sa5kQgrGGcLk0r1ihgUVAZp2bQJ0Yq9/dog.png",
        "prompt": "face of a ginger cat, high resolution, sitting on a park bench",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "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 cjwbw/stable-diffusion-v2-inpainting 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": "cjwbw/stable-diffusion-v2-inpainting:f9bb0632bfdceb83196e85521b9b55895f8ff3d1d3b487fd1973210c0eb30bec",
    "input": {
      "mask": "https://replicate.delivery/pbxt/HszfSoPGhMEvXf9Gf5gA564aMMyuki3TLSlQQmCepokDJy47/mask.png",
      "image": "https://replicate.delivery/pbxt/HszfS11BnkFTWHKv6sa5kQgrGGcLk0r1ihgUVAZp2bQJ0Yq9/dog.png",
      "prompt": "face of a ginger cat, high resolution, sitting on a park bench",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "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.

Output

{
  "completed_at": "2022-12-02T00:24:09.794366Z",
  "created_at": "2022-12-02T00:24:05.569413Z",
  "data_removed": false,
  "error": null,
  "id": "bjpmr5hqxjd5ri2kynk5ebtgaa",
  "input": {
    "mask": "https://replicate.delivery/pbxt/HszfSoPGhMEvXf9Gf5gA564aMMyuki3TLSlQQmCepokDJy47/mask.png",
    "image": "https://replicate.delivery/pbxt/HszfS11BnkFTWHKv6sa5kQgrGGcLk0r1ihgUVAZp2bQJ0Yq9/dog.png",
    "prompt": "face of a ginger cat, high resolution, sitting on a park bench",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 15524\n  0%|          | 0/51 [00:00<?, ?it/s]\n  4%|▍         | 2/51 [00:00<00:03, 14.35it/s]\n  8%|▊         | 4/51 [00:00<00:02, 15.70it/s]\n 12%|█▏        | 6/51 [00:00<00:02, 16.20it/s]\n 16%|█▌        | 8/51 [00:00<00:02, 16.51it/s]\n 20%|█▉        | 10/51 [00:00<00:02, 16.53it/s]\n 24%|██▎       | 12/51 [00:00<00:02, 16.22it/s]\n 27%|██▋       | 14/51 [00:00<00:02, 16.36it/s]\n 31%|███▏      | 16/51 [00:00<00:02, 16.47it/s]\n 35%|███▌      | 18/51 [00:01<00:02, 16.50it/s]\n 39%|███▉      | 20/51 [00:01<00:01, 16.54it/s]\n 43%|████▎     | 22/51 [00:01<00:01, 16.52it/s]\n 47%|████▋     | 24/51 [00:01<00:01, 16.52it/s]\n 51%|█████     | 26/51 [00:01<00:01, 16.54it/s]\n 55%|█████▍    | 28/51 [00:01<00:01, 16.37it/s]\n 59%|█████▉    | 30/51 [00:01<00:01, 16.47it/s]\n 63%|██████▎   | 32/51 [00:01<00:01, 16.54it/s]\n 67%|██████▋   | 34/51 [00:02<00:01, 16.58it/s]\n 71%|███████   | 36/51 [00:02<00:00, 16.56it/s]\n 75%|███████▍  | 38/51 [00:02<00:00, 16.54it/s]\n 78%|███████▊  | 40/51 [00:02<00:00, 16.59it/s]\n 82%|████████▏ | 42/51 [00:02<00:00, 16.65it/s]\n 86%|████████▋ | 44/51 [00:02<00:00, 16.65it/s]\n 90%|█████████ | 46/51 [00:02<00:00, 16.66it/s]\n 94%|█████████▍| 48/51 [00:02<00:00, 16.68it/s]\n 98%|█████████▊| 50/51 [00:03<00:00, 16.68it/s]\n100%|██████████| 51/51 [00:03<00:00, 16.49it/s]",
  "metrics": {
    "predict_time": 4.186986,
    "total_time": 4.224953
  },
  "output": [
    "https://replicate.delivery/pbxt/R0kqaA8PUMarFx2SoelD46bYGO8MwPUx1XiMUdq82YiUv3CIA/out-0.png"
  ],
  "started_at": "2022-12-02T00:24:05.607380Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bjpmr5hqxjd5ri2kynk5ebtgaa",
    "cancel": "https://api.replicate.com/v1/predictions/bjpmr5hqxjd5ri2kynk5ebtgaa/cancel"
  },
  "version": "f9bb0632bfdceb83196e85521b9b55895f8ff3d1d3b487fd1973210c0eb30bec"
}

Generated in

4.2 seconds

Tweak it Report

Examples

View more examples

Run time and cost

This model costs approximately $0.0092 to run on Replicate, or 108 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 A100 (80GB) GPU hardware. Predictions typically complete within 7 seconds. The predict time for this model varies significantly based on the inputs.

Readme

weights from: https://huggingface.co/stabilityai/stable-diffusion-2-inpainting

stable-diffusion-v2-inpainting

This stable-diffusion-2-inpainting model is resumed from stable-diffusion-2-base (512-base-ema.ckpt) and trained for another 200k steps. Follows the mask-generation strategy presented in LAMA which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning.