stability-ai / sdxl

{
  "width": 1024,
  "height": 1024,
  "prompt": "A studio photo of a rainbow coloured cat",
  "refine": "expert_ensemble_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A studio photo of a rainbow coloured cat",
      refine: "expert_ensemble_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A studio photo of a rainbow coloured cat",
        "refine": "expert_ensemble_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A studio photo of a rainbow coloured cat",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "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.

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A studio photo of a rainbow coloured cat"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A studio photo of a rainbow coloured cat",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T19:57:37.126174Z",
  "created_at": "2023-07-26T19:57:26.269769Z",
  "data_removed": false,
  "error": null,
  "id": "zuv3yw3bis3kvmypxkefqlowme",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A studio photo of a rainbow coloured cat",
    "refine": "expert_ensemble_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 48373\ntxt2img mode\n  0%|          | 0/31 [00:00<?, ?it/s]\n  3%|▎         | 1/31 [00:00<00:06,  4.98it/s]\n  6%|▋         | 2/31 [00:00<00:05,  4.95it/s]\n 10%|▉         | 3/31 [00:00<00:05,  4.93it/s]\n 13%|█▎        | 4/31 [00:00<00:05,  4.92it/s]\n 16%|█▌        | 5/31 [00:01<00:05,  4.90it/s]\n 19%|█▉        | 6/31 [00:01<00:05,  4.90it/s]\n 23%|██▎       | 7/31 [00:01<00:04,  4.90it/s]\n 26%|██▌       | 8/31 [00:01<00:04,  4.89it/s]\n 29%|██▉       | 9/31 [00:01<00:04,  4.89it/s]\n 32%|███▏      | 10/31 [00:02<00:04,  4.90it/s]\n 35%|███▌      | 11/31 [00:02<00:04,  4.89it/s]\n 39%|███▊      | 12/31 [00:02<00:03,  4.89it/s]\n 42%|████▏     | 13/31 [00:02<00:03,  4.89it/s]\n 45%|████▌     | 14/31 [00:02<00:03,  4.89it/s]\n 48%|████▊     | 15/31 [00:03<00:03,  4.89it/s]\n 52%|█████▏    | 16/31 [00:03<00:03,  4.90it/s]\n 55%|█████▍    | 17/31 [00:03<00:02,  4.89it/s]\n 58%|█████▊    | 18/31 [00:03<00:02,  4.89it/s]\n 61%|██████▏   | 19/31 [00:03<00:02,  4.89it/s]\n 65%|██████▍   | 20/31 [00:04<00:02,  4.89it/s]\n 68%|██████▊   | 21/31 [00:04<00:02,  4.89it/s]\n 71%|███████   | 22/31 [00:04<00:01,  4.89it/s]\n 74%|███████▍  | 23/31 [00:04<00:01,  4.89it/s]\n 77%|███████▋  | 24/31 [00:04<00:01,  4.89it/s]\n 81%|████████  | 25/31 [00:05<00:01,  4.89it/s]\n 84%|████████▍ | 26/31 [00:05<00:01,  4.88it/s]\n 87%|████████▋ | 27/31 [00:05<00:00,  4.88it/s]\n 90%|█████████ | 28/31 [00:05<00:00,  4.89it/s]\n 94%|█████████▎| 29/31 [00:05<00:00,  4.89it/s]\n 97%|█████████▋| 30/31 [00:06<00:00,  4.89it/s]\n100%|██████████| 31/31 [00:06<00:00,  4.90it/s]\n100%|██████████| 31/31 [00:06<00:00,  4.90it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:02,  4.34it/s]\n 20%|██        | 2/10 [00:00<00:01,  4.31it/s]\n 30%|███       | 3/10 [00:00<00:01,  4.31it/s]\n 40%|████      | 4/10 [00:00<00:01,  4.30it/s]\n 50%|█████     | 5/10 [00:01<00:01,  4.30it/s]\n 60%|██████    | 6/10 [00:01<00:00,  4.30it/s]\n 70%|███████   | 7/10 [00:01<00:00,  4.30it/s]\n 80%|████████  | 8/10 [00:01<00:00,  4.29it/s]\n 90%|█████████ | 9/10 [00:02<00:00,  4.30it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.29it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.30it/s]",
  "metrics": {
    "predict_time": 10.8524,
    "total_time": 10.856405
  },
  "output": [
    "https://replicate.delivery/pbxt/V1IpaG4oVXofGyZcPxhhVVfEFvaMx9lMzqR9Fh4RpsRwyyTRA/out-0.png"
  ],
  "started_at": "2023-07-26T19:57:26.273774Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zuv3yw3bis3kvmypxkefqlowme",
    "cancel": "https://api.replicate.com/v1/predictions/zuv3yw3bis3kvmypxkefqlowme/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

10.9 seconds

Tweak it ShareReport

Using seed: 48373
txt2img mode
  0%|          | 0/31 [00:00<?, ?it/s]
  3%|▎         | 1/31 [00:00<00:06,  4.98it/s]
  6%|▋         | 2/31 [00:00<00:05,  4.95it/s]
 10%|▉         | 3/31 [00:00<00:05,  4.93it/s]
 13%|█▎        | 4/31 [00:00<00:05,  4.92it/s]
 16%|█▌        | 5/31 [00:01<00:05,  4.90it/s]
 19%|█▉        | 6/31 [00:01<00:05,  4.90it/s]
 23%|██▎       | 7/31 [00:01<00:04,  4.90it/s]
 26%|██▌       | 8/31 [00:01<00:04,  4.89it/s]
 29%|██▉       | 9/31 [00:01<00:04,  4.89it/s]
 32%|███▏      | 10/31 [00:02<00:04,  4.90it/s]
 35%|███▌      | 11/31 [00:02<00:04,  4.89it/s]
 39%|███▊      | 12/31 [00:02<00:03,  4.89it/s]
 42%|████▏     | 13/31 [00:02<00:03,  4.89it/s]
 45%|████▌     | 14/31 [00:02<00:03,  4.89it/s]
 48%|████▊     | 15/31 [00:03<00:03,  4.89it/s]
 52%|█████▏    | 16/31 [00:03<00:03,  4.90it/s]
 55%|█████▍    | 17/31 [00:03<00:02,  4.89it/s]
 58%|█████▊    | 18/31 [00:03<00:02,  4.89it/s]
 61%|██████▏   | 19/31 [00:03<00:02,  4.89it/s]
 65%|██████▍   | 20/31 [00:04<00:02,  4.89it/s]
 68%|██████▊   | 21/31 [00:04<00:02,  4.89it/s]
 71%|███████   | 22/31 [00:04<00:01,  4.89it/s]
 74%|███████▍  | 23/31 [00:04<00:01,  4.89it/s]
 77%|███████▋  | 24/31 [00:04<00:01,  4.89it/s]
 81%|████████  | 25/31 [00:05<00:01,  4.89it/s]
 84%|████████▍ | 26/31 [00:05<00:01,  4.88it/s]
 87%|████████▋ | 27/31 [00:05<00:00,  4.88it/s]
 90%|█████████ | 28/31 [00:05<00:00,  4.89it/s]
 94%|█████████▎| 29/31 [00:05<00:00,  4.89it/s]
 97%|█████████▋| 30/31 [00:06<00:00,  4.89it/s]
100%|██████████| 31/31 [00:06<00:00,  4.90it/s]
100%|██████████| 31/31 [00:06<00:00,  4.90it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:00<00:02,  4.34it/s]
 20%|██        | 2/10 [00:00<00:01,  4.31it/s]
 30%|███       | 3/10 [00:00<00:01,  4.31it/s]
 40%|████      | 4/10 [00:00<00:01,  4.30it/s]
 50%|█████     | 5/10 [00:01<00:01,  4.30it/s]
 60%|██████    | 6/10 [00:01<00:00,  4.30it/s]
 70%|███████   | 7/10 [00:01<00:00,  4.30it/s]
 80%|████████  | 8/10 [00:01<00:00,  4.29it/s]
 90%|█████████ | 9/10 [00:02<00:00,  4.30it/s]
100%|██████████| 10/10 [00:02<00:00,  4.29it/s]
100%|██████████| 10/10 [00:02<00:00,  4.30it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:610dddf0

faz67o3bvxmrr5ydw7yhustwfq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

33.5s

Created

over 1 year ago by @stability-ai

Input

mask
image
width: 1024
height: 1024
prompt: An orange cat sitting on a bench
refine: base_image_refiner
scheduler: KarrasDPM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
prompt_strength: 0.8
num_inference_steps: 25

{
  "mask": "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
  "image": "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
  "width": 1024,
  "height": 1024,
  "prompt": "An orange cat sitting on a bench",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
      image: "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
      width: 1024,
      height: 1024,
      prompt: "An orange cat sitting on a bench",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "mask": "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
        "image": "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
        "width": 1024,
        "height": 1024,
        "prompt": "An orange cat sitting on a bench",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "mask": "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
      "image": "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
      "width": 1024,
      "height": 1024,
      "prompt": "An orange cat sitting on a bench",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'mask="https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png"' \
  -i 'image="https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="An orange cat sitting on a bench"' \
  -i 'refine="base_image_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "mask": "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
      "image": "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
      "width": 1024,
      "height": 1024,
      "prompt": "An orange cat sitting on a bench",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "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": "2023-07-26T19:59:46.932300Z",
  "created_at": "2023-07-26T19:59:13.479776Z",
  "data_removed": false,
  "error": null,
  "id": "faz67o3bvxmrr5ydw7yhustwfq",
  "input": {
    "mask": "https://replicate.delivery/pbxt/JF3Ld3yPLVA3JIELHx1uaAV5CQOyr4AoiOfo6mJZn2fofGaT/dog-mask.png",
    "image": "https://replicate.delivery/pbxt/JF3LddQgRiMM9Q4Smyfw7q7BR9Gn0PwkSWvJjKDPxyvr8Ru0/cool-dog.png",
    "width": 1024,
    "height": 1024,
    "prompt": "An orange cat sitting on a bench",
    "refine": "base_image_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.8,
    "num_inference_steps": 25
  },
  "logs": "Using seed: 47363\ninpainting mode\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.62it/s]\n 10%|█         | 2/20 [00:00<00:03,  4.84it/s]\n 15%|█▌        | 3/20 [00:00<00:03,  4.91it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.94it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.95it/s]\n 30%|███       | 6/20 [00:01<00:02,  4.96it/s]\n 35%|███▌      | 7/20 [00:01<00:02,  4.96it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.96it/s]\n 45%|████▌     | 9/20 [00:01<00:02,  4.97it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.98it/s]\n 55%|█████▌    | 11/20 [00:02<00:01,  4.98it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.98it/s]\n 65%|██████▌   | 13/20 [00:02<00:01,  4.98it/s]\n 70%|███████   | 14/20 [00:02<00:01,  4.98it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  4.97it/s]\n 80%|████████  | 16/20 [00:03<00:00,  4.97it/s]\n 85%|████████▌ | 17/20 [00:03<00:00,  4.97it/s]\n 90%|█████████ | 18/20 [00:03<00:00,  4.96it/s]\n 95%|█████████▌| 19/20 [00:03<00:00,  4.96it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.96it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.95it/s]\n  0%|          | 0/7 [00:00<?, ?it/s]\n 14%|█▍        | 1/7 [00:00<00:01,  4.25it/s]\n 29%|██▊       | 2/7 [00:00<00:01,  4.30it/s]\n 43%|████▎     | 3/7 [00:00<00:00,  4.31it/s]\n 57%|█████▋    | 4/7 [00:00<00:00,  4.32it/s]\n 71%|███████▏  | 5/7 [00:01<00:00,  4.33it/s]\n 86%|████████▌ | 6/7 [00:01<00:00,  4.33it/s]\n100%|██████████| 7/7 [00:01<00:00,  4.33it/s]\n100%|██████████| 7/7 [00:01<00:00,  4.32it/s]",
  "metrics": {
    "predict_time": 10.301413,
    "total_time": 33.452524
  },
  "output": [
    "https://replicate.delivery/pbxt/p6Pt5qCuQGYGDxzAbB3goyeFguncwZ8EPj8Ncl7JPhCZa5pIA/out-0.png"
  ],
  "started_at": "2023-07-26T19:59:36.630887Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/faz67o3bvxmrr5ydw7yhustwfq",
    "cancel": "https://api.replicate.com/v1/predictions/faz67o3bvxmrr5ydw7yhustwfq/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

10.3 seconds

Tweak it ShareReport

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:610dddf0

54q24ulbyhpgb3gmbs2yryboa4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

11.4s

Created

over 1 year ago by @stability-ai

Input

width: 1344
height: 768
prompt: A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful
refine: expert_ensemble_refiner
scheduler: KarrasDPM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
negative_prompt: soft, blurry, ugly
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1344,
  "height": 768,
  "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
  "refine": "expert_ensemble_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "negative_prompt": "soft, blurry, ugly",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      width: 1344,
      height: 768,
      prompt: "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
      refine: "expert_ensemble_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      negative_prompt: "soft, blurry, ugly",
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "width": 1344,
        "height": 768,
        "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
        "refine": "expert_ensemble_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "negative_prompt": "soft, blurry, ugly",
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "width": 1344,
      "height": 768,
      "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "negative_prompt": "soft, blurry, ugly",
      "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.

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'width=1344' \
  -i 'height=768' \
  -i 'prompt="A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'negative_prompt="soft, blurry, ugly"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1344,
      "height": 768,
      "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "negative_prompt": "soft, blurry, ugly",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T20:04:41.674898Z",
  "created_at": "2023-07-26T20:04:30.299979Z",
  "data_removed": false,
  "error": null,
  "id": "54q24ulbyhpgb3gmbs2yryboa4",
  "input": {
    "width": 1344,
    "height": 768,
    "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful",
    "refine": "expert_ensemble_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "negative_prompt": "soft, blurry, ugly",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 48161\ntxt2img mode\n  0%|          | 0/31 [00:00<?, ?it/s]\n  3%|▎         | 1/31 [00:00<00:23,  1.26it/s]\n  6%|▋         | 2/31 [00:00<00:12,  2.27it/s]\n 10%|▉         | 3/31 [00:01<00:09,  3.03it/s]\n 13%|█▎        | 4/31 [00:01<00:07,  3.60it/s]\n 16%|█▌        | 5/31 [00:01<00:06,  4.01it/s]\n 19%|█▉        | 6/31 [00:01<00:05,  4.30it/s]\n 23%|██▎       | 7/31 [00:01<00:05,  4.52it/s]\n 26%|██▌       | 8/31 [00:02<00:04,  4.68it/s]\n 29%|██▉       | 9/31 [00:02<00:04,  4.79it/s]\n 32%|███▏      | 10/31 [00:02<00:04,  4.86it/s]\n 35%|███▌      | 11/31 [00:02<00:04,  4.91it/s]\n 39%|███▊      | 12/31 [00:02<00:03,  4.95it/s]\n 42%|████▏     | 13/31 [00:03<00:03,  4.98it/s]\n 45%|████▌     | 14/31 [00:03<00:03,  5.00it/s]\n 48%|████▊     | 15/31 [00:03<00:03,  5.01it/s]\n 52%|█████▏    | 16/31 [00:03<00:02,  5.02it/s]\n 55%|█████▍    | 17/31 [00:03<00:02,  5.02it/s]\n 58%|█████▊    | 18/31 [00:04<00:02,  5.03it/s]\n 61%|██████▏   | 19/31 [00:04<00:02,  5.04it/s]\n 65%|██████▍   | 20/31 [00:04<00:02,  5.05it/s]\n 68%|██████▊   | 21/31 [00:04<00:01,  5.05it/s]\n 71%|███████   | 22/31 [00:04<00:01,  5.06it/s]\n 74%|███████▍  | 23/31 [00:05<00:01,  5.06it/s]\n 77%|███████▋  | 24/31 [00:05<00:01,  5.06it/s]\n 81%|████████  | 25/31 [00:05<00:01,  5.07it/s]\n 84%|████████▍ | 26/31 [00:05<00:00,  5.06it/s]\n 87%|████████▋ | 27/31 [00:05<00:00,  5.06it/s]\n 90%|█████████ | 28/31 [00:06<00:00,  5.06it/s]\n 94%|█████████▎| 29/31 [00:06<00:00,  5.06it/s]\n 97%|█████████▋| 30/31 [00:06<00:00,  5.06it/s]\n100%|██████████| 31/31 [00:06<00:00,  5.06it/s]\n100%|██████████| 31/31 [00:06<00:00,  4.61it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:02,  4.30it/s]\n 20%|██        | 2/10 [00:00<00:01,  4.37it/s]\n 30%|███       | 3/10 [00:00<00:01,  4.38it/s]\n 40%|████      | 4/10 [00:00<00:01,  4.39it/s]\n 50%|█████     | 5/10 [00:01<00:01,  4.39it/s]\n 60%|██████    | 6/10 [00:01<00:00,  4.40it/s]\n 70%|███████   | 7/10 [00:01<00:00,  4.40it/s]\n 80%|████████  | 8/10 [00:01<00:00,  4.40it/s]\n 90%|█████████ | 9/10 [00:02<00:00,  4.40it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.40it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.39it/s]",
  "metrics": {
    "predict_time": 11.358785,
    "total_time": 11.374919
  },
  "output": [
    "https://replicate.delivery/pbxt/mBv308Qw3DafE6vOg7a2eNPTDkZMRwRZ5XdDGZzGkdnZ5yTRA/out-0.png"
  ],
  "started_at": "2023-07-26T20:04:30.316113Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/54q24ulbyhpgb3gmbs2yryboa4",
    "cancel": "https://api.replicate.com/v1/predictions/54q24ulbyhpgb3gmbs2yryboa4/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

11.4 seconds

Tweak it ShareReport

Using seed: 48161
txt2img mode
  0%|          | 0/31 [00:00<?, ?it/s]
  3%|▎         | 1/31 [00:00<00:23,  1.26it/s]
  6%|▋         | 2/31 [00:00<00:12,  2.27it/s]
 10%|▉         | 3/31 [00:01<00:09,  3.03it/s]
 13%|█▎        | 4/31 [00:01<00:07,  3.60it/s]
 16%|█▌        | 5/31 [00:01<00:06,  4.01it/s]
 19%|█▉        | 6/31 [00:01<00:05,  4.30it/s]
 23%|██▎       | 7/31 [00:01<00:05,  4.52it/s]
 26%|██▌       | 8/31 [00:02<00:04,  4.68it/s]
 29%|██▉       | 9/31 [00:02<00:04,  4.79it/s]
 32%|███▏      | 10/31 [00:02<00:04,  4.86it/s]
 35%|███▌      | 11/31 [00:02<00:04,  4.91it/s]
 39%|███▊      | 12/31 [00:02<00:03,  4.95it/s]
 42%|████▏     | 13/31 [00:03<00:03,  4.98it/s]
 45%|████▌     | 14/31 [00:03<00:03,  5.00it/s]
 48%|████▊     | 15/31 [00:03<00:03,  5.01it/s]
 52%|█████▏    | 16/31 [00:03<00:02,  5.02it/s]
 55%|█████▍    | 17/31 [00:03<00:02,  5.02it/s]
 58%|█████▊    | 18/31 [00:04<00:02,  5.03it/s]
 61%|██████▏   | 19/31 [00:04<00:02,  5.04it/s]
 65%|██████▍   | 20/31 [00:04<00:02,  5.05it/s]
 68%|██████▊   | 21/31 [00:04<00:01,  5.05it/s]
 71%|███████   | 22/31 [00:04<00:01,  5.06it/s]
 74%|███████▍  | 23/31 [00:05<00:01,  5.06it/s]
 77%|███████▋  | 24/31 [00:05<00:01,  5.06it/s]
 81%|████████  | 25/31 [00:05<00:01,  5.07it/s]
 84%|████████▍ | 26/31 [00:05<00:00,  5.06it/s]
 87%|████████▋ | 27/31 [00:05<00:00,  5.06it/s]
 90%|█████████ | 28/31 [00:06<00:00,  5.06it/s]
 94%|█████████▎| 29/31 [00:06<00:00,  5.06it/s]
 97%|█████████▋| 30/31 [00:06<00:00,  5.06it/s]
100%|██████████| 31/31 [00:06<00:00,  5.06it/s]
100%|██████████| 31/31 [00:06<00:00,  4.61it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:00<00:02,  4.30it/s]
 20%|██        | 2/10 [00:00<00:01,  4.37it/s]
 30%|███       | 3/10 [00:00<00:01,  4.38it/s]
 40%|████      | 4/10 [00:00<00:01,  4.39it/s]
 50%|█████     | 5/10 [00:01<00:01,  4.39it/s]
 60%|██████    | 6/10 [00:01<00:00,  4.40it/s]
 70%|███████   | 7/10 [00:01<00:00,  4.40it/s]
 80%|████████  | 8/10 [00:01<00:00,  4.40it/s]
 90%|█████████ | 9/10 [00:02<00:00,  4.40it/s]
100%|██████████| 10/10 [00:02<00:00,  4.40it/s]
100%|██████████| 10/10 [00:02<00:00,  4.39it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:610dddf0

wv7kgx3bgsguc3cnltku6me4py

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

9.7s

Created

over 1 year ago

Input

mask
image
width: 1024
height: 1024
prompt: Alien invasion
refine: base_image_refiner
scheduler: KarrasDPM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
prompt_strength: 0.9
num_inference_steps: 30

{
  "mask": "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
  "image": "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
  "width": 1024,
  "height": 1024,
  "prompt": "Alien invasion",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.9,
  "num_inference_steps": 30
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
      image: "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
      width: 1024,
      height: 1024,
      prompt: "Alien invasion",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      prompt_strength: 0.9,
      num_inference_steps: 30
    }
  }
);

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

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "mask": "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
        "image": "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
        "width": 1024,
        "height": 1024,
        "prompt": "Alien invasion",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "prompt_strength": 0.9,
        "num_inference_steps": 30
    }
)
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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "mask": "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
      "image": "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
      "width": 1024,
      "height": 1024,
      "prompt": "Alien invasion",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.9,
      "num_inference_steps": 30
    }
  }' \
  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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'mask="https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png"' \
  -i 'image="https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="Alien invasion"' \
  -i 'refine="base_image_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'prompt_strength=0.9' \
  -i 'num_inference_steps=30'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "mask": "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
      "image": "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
      "width": 1024,
      "height": 1024,
      "prompt": "Alien invasion",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.9,
      "num_inference_steps": 30
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T20:07:34.580706Z",
  "created_at": "2023-07-26T20:07:24.863629Z",
  "data_removed": false,
  "error": null,
  "id": "wv7kgx3bgsguc3cnltku6me4py",
  "input": {
    "mask": "https://replicate.delivery/pbxt/JF3OMU8P5Kpxi4EmDqDKEH1fxE5qGOZThplanZAXnzJzzVja/nyc-mask.png",
    "image": "https://replicate.delivery/pbxt/JF3OMzdRCDSp9ZL2bxRDb6YZWryrT0OxfTB60W4y5PFA6MYi/nyc.png",
    "width": 1024,
    "height": 1024,
    "prompt": "Alien invasion",
    "refine": "base_image_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.9,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 20832\ninpainting mode\n  0%|          | 0/27 [00:00<?, ?it/s]\n  4%|▎         | 1/27 [00:00<00:05,  5.01it/s]\n  7%|▋         | 2/27 [00:00<00:04,  5.00it/s]\n 11%|█         | 3/27 [00:00<00:04,  5.00it/s]\n 15%|█▍        | 4/27 [00:00<00:04,  5.00it/s]\n 19%|█▊        | 5/27 [00:01<00:04,  4.99it/s]\n 22%|██▏       | 6/27 [00:01<00:04,  4.99it/s]\n 26%|██▌       | 7/27 [00:01<00:04,  4.99it/s]\n 30%|██▉       | 8/27 [00:01<00:03,  4.99it/s]\n 33%|███▎      | 9/27 [00:01<00:03,  4.99it/s]\n 37%|███▋      | 10/27 [00:02<00:03,  4.99it/s]\n 41%|████      | 11/27 [00:02<00:03,  4.99it/s]\n 44%|████▍     | 12/27 [00:02<00:03,  4.98it/s]\n 48%|████▊     | 13/27 [00:02<00:02,  4.98it/s]\n 52%|█████▏    | 14/27 [00:02<00:02,  4.97it/s]\n 56%|█████▌    | 15/27 [00:03<00:02,  4.97it/s]\n 59%|█████▉    | 16/27 [00:03<00:02,  4.96it/s]\n 63%|██████▎   | 17/27 [00:03<00:02,  4.95it/s]\n 67%|██████▋   | 18/27 [00:03<00:01,  4.95it/s]\n 70%|███████   | 19/27 [00:03<00:01,  4.96it/s]\n 74%|███████▍  | 20/27 [00:04<00:01,  4.96it/s]\n 78%|███████▊  | 21/27 [00:04<00:01,  4.96it/s]\n 81%|████████▏ | 22/27 [00:04<00:01,  4.96it/s]\n 85%|████████▌ | 23/27 [00:04<00:00,  4.95it/s]\n 89%|████████▉ | 24/27 [00:04<00:00,  4.96it/s]\n 93%|█████████▎| 25/27 [00:05<00:00,  4.96it/s]\n 96%|█████████▋| 26/27 [00:05<00:00,  4.96it/s]\n100%|██████████| 27/27 [00:05<00:00,  4.95it/s]\n100%|██████████| 27/27 [00:05<00:00,  4.97it/s]\n  0%|          | 0/9 [00:00<?, ?it/s]\n 11%|█         | 1/9 [00:00<00:01,  4.36it/s]\n 22%|██▏       | 2/9 [00:00<00:01,  4.34it/s]\n 33%|███▎      | 3/9 [00:00<00:01,  4.33it/s]\n 44%|████▍     | 4/9 [00:00<00:01,  4.33it/s]\n 56%|█████▌    | 5/9 [00:01<00:00,  4.33it/s]\n 67%|██████▋   | 6/9 [00:01<00:00,  4.32it/s]\n 78%|███████▊  | 7/9 [00:01<00:00,  4.33it/s]\n 89%|████████▉ | 8/9 [00:01<00:00,  4.32it/s]\n100%|██████████| 9/9 [00:02<00:00,  4.32it/s]\n100%|██████████| 9/9 [00:02<00:00,  4.33it/s]",
  "metrics": {
    "predict_time": 9.733889,
    "total_time": 9.717077
  },
  "output": [
    "https://replicate.delivery/pbxt/cA9288tEJXbcJNBA6OU3gDJ9LWWCFCfDllhoefA8h2VN4lniA/out-0.png"
  ],
  "started_at": "2023-07-26T20:07:24.846817Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wv7kgx3bgsguc3cnltku6me4py",
    "cancel": "https://api.replicate.com/v1/predictions/wv7kgx3bgsguc3cnltku6me4py/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

9.7 seconds

Tweak it ShareReport

Using seed: 20832
inpainting mode
  0%|          | 0/27 [00:00<?, ?it/s]
  4%|▎         | 1/27 [00:00<00:05,  5.01it/s]
  7%|▋         | 2/27 [00:00<00:04,  5.00it/s]
 11%|█         | 3/27 [00:00<00:04,  5.00it/s]
 15%|█▍        | 4/27 [00:00<00:04,  5.00it/s]
 19%|█▊        | 5/27 [00:01<00:04,  4.99it/s]
 22%|██▏       | 6/27 [00:01<00:04,  4.99it/s]
 26%|██▌       | 7/27 [00:01<00:04,  4.99it/s]
 30%|██▉       | 8/27 [00:01<00:03,  4.99it/s]
 33%|███▎      | 9/27 [00:01<00:03,  4.99it/s]
 37%|███▋      | 10/27 [00:02<00:03,  4.99it/s]
 41%|████      | 11/27 [00:02<00:03,  4.99it/s]
 44%|████▍     | 12/27 [00:02<00:03,  4.98it/s]
 48%|████▊     | 13/27 [00:02<00:02,  4.98it/s]
 52%|█████▏    | 14/27 [00:02<00:02,  4.97it/s]
 56%|█████▌    | 15/27 [00:03<00:02,  4.97it/s]
 59%|█████▉    | 16/27 [00:03<00:02,  4.96it/s]
 63%|██████▎   | 17/27 [00:03<00:02,  4.95it/s]
 67%|██████▋   | 18/27 [00:03<00:01,  4.95it/s]
 70%|███████   | 19/27 [00:03<00:01,  4.96it/s]
 74%|███████▍  | 20/27 [00:04<00:01,  4.96it/s]
 78%|███████▊  | 21/27 [00:04<00:01,  4.96it/s]
 81%|████████▏ | 22/27 [00:04<00:01,  4.96it/s]
 85%|████████▌ | 23/27 [00:04<00:00,  4.95it/s]
 89%|████████▉ | 24/27 [00:04<00:00,  4.96it/s]
 93%|█████████▎| 25/27 [00:05<00:00,  4.96it/s]
 96%|█████████▋| 26/27 [00:05<00:00,  4.96it/s]
100%|██████████| 27/27 [00:05<00:00,  4.95it/s]
100%|██████████| 27/27 [00:05<00:00,  4.97it/s]
  0%|          | 0/9 [00:00<?, ?it/s]
 11%|█         | 1/9 [00:00<00:01,  4.36it/s]
 22%|██▏       | 2/9 [00:00<00:01,  4.34it/s]
 33%|███▎      | 3/9 [00:00<00:01,  4.33it/s]
 44%|████▍     | 4/9 [00:00<00:01,  4.33it/s]
 56%|█████▌    | 5/9 [00:01<00:00,  4.33it/s]
 67%|██████▋   | 6/9 [00:01<00:00,  4.32it/s]
 78%|███████▊  | 7/9 [00:01<00:00,  4.33it/s]
 89%|████████▉ | 8/9 [00:01<00:00,  4.32it/s]
100%|██████████| 9/9 [00:02<00:00,  4.32it/s]
100%|██████████| 9/9 [00:02<00:00,  4.33it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:610dddf0

ks4e2jdb6zef4xodz3mz5utuu4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

7.8s

Created

over 1 year ago by @stability-ai

Input

image
width: 1024
height: 1024
prompt: A rainbow coloured tiger
refine: expert_ensemble_refiner
scheduler: KarrasDPM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
prompt_strength: 0.65
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
  "width": 1024,
  "height": 1024,
  "prompt": "A rainbow coloured tiger",
  "refine": "expert_ensemble_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.65,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      width: 1024,
      height: 1024,
      prompt: "A rainbow coloured tiger",
      refine: "expert_ensemble_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      prompt_strength: 0.65,
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
        "width": 1024,
        "height": 1024,
        "prompt": "A rainbow coloured tiger",
        "refine": "expert_ensemble_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "prompt_strength": 0.65,
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      "width": 1024,
      "height": 1024,
      "prompt": "A rainbow coloured tiger",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.65,
      "num_inference_steps": 50
    }
  }' \
  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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'image="https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A rainbow coloured tiger"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'prompt_strength=0.65' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      "width": 1024,
      "height": 1024,
      "prompt": "A rainbow coloured tiger",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.65,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T20:20:38.861038Z",
  "created_at": "2023-07-26T20:20:31.036768Z",
  "data_removed": false,
  "error": null,
  "id": "ks4e2jdb6zef4xodz3mz5utuu4",
  "input": {
    "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
    "width": 1024,
    "height": 1024,
    "prompt": "A rainbow coloured tiger",
    "refine": "expert_ensemble_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.65,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 47500\nimg2img mode\n  0%|          | 0/13 [00:00<?, ?it/s]\n  8%|▊         | 1/13 [00:00<00:02,  4.99it/s]\n 15%|█▌        | 2/13 [00:00<00:02,  4.98it/s]\n 23%|██▎       | 3/13 [00:00<00:02,  4.98it/s]\n 31%|███       | 4/13 [00:00<00:01,  4.98it/s]\n 38%|███▊      | 5/13 [00:01<00:01,  4.97it/s]\n 46%|████▌     | 6/13 [00:01<00:01,  4.96it/s]\n 54%|█████▍    | 7/13 [00:01<00:01,  4.97it/s]\n 62%|██████▏   | 8/13 [00:01<00:01,  4.97it/s]\n 69%|██████▉   | 9/13 [00:01<00:00,  4.97it/s]\n 77%|███████▋  | 10/13 [00:02<00:00,  4.96it/s]\n 85%|████████▍ | 11/13 [00:02<00:00,  4.96it/s]\n 92%|█████████▏| 12/13 [00:02<00:00,  4.96it/s]\n100%|██████████| 13/13 [00:02<00:00,  4.95it/s]\n100%|██████████| 13/13 [00:02<00:00,  4.97it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:02,  4.24it/s]\n 20%|██        | 2/10 [00:00<00:01,  4.29it/s]\n 30%|███       | 3/10 [00:00<00:01,  4.31it/s]\n 40%|████      | 4/10 [00:00<00:01,  4.31it/s]\n 50%|█████     | 5/10 [00:01<00:01,  4.32it/s]\n 60%|██████    | 6/10 [00:01<00:00,  4.32it/s]\n 70%|███████   | 7/10 [00:01<00:00,  4.32it/s]\n 80%|████████  | 8/10 [00:01<00:00,  4.32it/s]\n 90%|█████████ | 9/10 [00:02<00:00,  4.32it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.32it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.31it/s]",
  "metrics": {
    "predict_time": 7.829192,
    "total_time": 7.82427
  },
  "output": [
    "https://replicate.delivery/pbxt/YhL0f6v0tfhmlEjce0iA2jFLW5vuKDbUh69FYNjnfQEXhMPFB/out-0.png"
  ],
  "started_at": "2023-07-26T20:20:31.031846Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ks4e2jdb6zef4xodz3mz5utuu4",
    "cancel": "https://api.replicate.com/v1/predictions/ks4e2jdb6zef4xodz3mz5utuu4/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

7.8 seconds

Tweak it ShareReport

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:610dddf0

lrmn5btbq2o5xpbksl56fw4y64

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

10.7s

Created

over 1 year ago by @stability-ai

Input

width: 1248
height: 832
prompt: A beautiful landscape photo
refine: expert_ensemble_refiner
scheduler: KarrasDPM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
negative_prompt: soft, blurry, ugly
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1248,
  "height": 832,
  "prompt": "A beautiful landscape photo",
  "refine": "expert_ensemble_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "negative_prompt": "soft, blurry, ugly",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      width: 1248,
      height: 832,
      prompt: "A beautiful landscape photo",
      refine: "expert_ensemble_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      negative_prompt: "soft, blurry, ugly",
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "width": 1248,
        "height": 832,
        "prompt": "A beautiful landscape photo",
        "refine": "expert_ensemble_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "negative_prompt": "soft, blurry, ugly",
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "width": 1248,
      "height": 832,
      "prompt": "A beautiful landscape photo",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "negative_prompt": "soft, blurry, ugly",
      "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.

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'width=1248' \
  -i 'height=832' \
  -i 'prompt="A beautiful landscape photo"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'negative_prompt="soft, blurry, ugly"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1248,
      "height": 832,
      "prompt": "A beautiful landscape photo",
      "refine": "expert_ensemble_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "negative_prompt": "soft, blurry, ugly",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T20:01:03.053313Z",
  "created_at": "2023-07-26T20:00:52.342022Z",
  "data_removed": false,
  "error": null,
  "id": "lrmn5btbq2o5xpbksl56fw4y64",
  "input": {
    "width": 1248,
    "height": 832,
    "prompt": "A beautiful landscape photo",
    "refine": "expert_ensemble_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "negative_prompt": "soft, blurry, ugly",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 58684\ntxt2img mode\n  0%|          | 0/31 [00:00<?, ?it/s]\n  3%|▎         | 1/31 [00:00<00:06,  4.80it/s]\n  6%|▋         | 2/31 [00:00<00:05,  4.89it/s]\n 10%|▉         | 3/31 [00:00<00:05,  4.92it/s]\n 13%|█▎        | 4/31 [00:00<00:05,  4.94it/s]\n 16%|█▌        | 5/31 [00:01<00:05,  4.95it/s]\n 19%|█▉        | 6/31 [00:01<00:05,  4.95it/s]\n 23%|██▎       | 7/31 [00:01<00:04,  4.97it/s]\n 26%|██▌       | 8/31 [00:01<00:04,  4.97it/s]\n 29%|██▉       | 9/31 [00:01<00:04,  4.98it/s]\n 32%|███▏      | 10/31 [00:02<00:04,  4.98it/s]\n 35%|███▌      | 11/31 [00:02<00:04,  4.97it/s]\n 39%|███▊      | 12/31 [00:02<00:03,  4.98it/s]\n 42%|████▏     | 13/31 [00:02<00:03,  4.98it/s]\n 45%|████▌     | 14/31 [00:02<00:03,  4.99it/s]\n 48%|████▊     | 15/31 [00:03<00:03,  4.98it/s]\n 52%|█████▏    | 16/31 [00:03<00:03,  4.98it/s]\n 55%|█████▍    | 17/31 [00:03<00:02,  4.98it/s]\n 58%|█████▊    | 18/31 [00:03<00:02,  4.98it/s]\n 61%|██████▏   | 19/31 [00:03<00:02,  4.98it/s]\n 65%|██████▍   | 20/31 [00:04<00:02,  4.97it/s]\n 68%|██████▊   | 21/31 [00:04<00:02,  4.98it/s]\n 71%|███████   | 22/31 [00:04<00:01,  4.97it/s]\n 74%|███████▍  | 23/31 [00:04<00:01,  4.97it/s]\n 77%|███████▋  | 24/31 [00:04<00:01,  4.97it/s]\n 81%|████████  | 25/31 [00:05<00:01,  4.97it/s]\n 84%|████████▍ | 26/31 [00:05<00:01,  4.97it/s]\n 87%|████████▋ | 27/31 [00:05<00:00,  4.97it/s]\n 90%|█████████ | 28/31 [00:05<00:00,  4.97it/s]\n 94%|█████████▎| 29/31 [00:05<00:00,  4.97it/s]\n 97%|█████████▋| 30/31 [00:06<00:00,  4.97it/s]\n100%|██████████| 31/31 [00:06<00:00,  4.97it/s]\n100%|██████████| 31/31 [00:06<00:00,  4.97it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:02,  4.15it/s]\n 20%|██        | 2/10 [00:00<00:01,  4.21it/s]\n 30%|███       | 3/10 [00:00<00:01,  4.23it/s]\n 40%|████      | 4/10 [00:00<00:01,  4.24it/s]\n 50%|█████     | 5/10 [00:01<00:01,  4.24it/s]\n 60%|██████    | 6/10 [00:01<00:00,  4.24it/s]\n 70%|███████   | 7/10 [00:01<00:00,  4.24it/s]\n 80%|████████  | 8/10 [00:01<00:00,  4.24it/s]\n 90%|█████████ | 9/10 [00:02<00:00,  4.24it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.24it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.24it/s]",
  "metrics": {
    "predict_time": 10.725354,
    "total_time": 10.711291
  },
  "output": [
    "https://replicate.delivery/pbxt/zIPS4uyGONKvKBg9iTA6FRC785eK7eWhpewpR7W0RnF9rlniA/out-0.png"
  ],
  "started_at": "2023-07-26T20:00:52.327959Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/lrmn5btbq2o5xpbksl56fw4y64",
    "cancel": "https://api.replicate.com/v1/predictions/lrmn5btbq2o5xpbksl56fw4y64/cancel"
  },
  "version": "610dddf033f10431b1b55f24510b6009fcba23017ee551a1b9afbc4eec79e29c"
}

Generated in

10.7 seconds

Tweak it ShareReport

Using seed: 58684
txt2img mode
  0%|          | 0/31 [00:00<?, ?it/s]
  3%|▎         | 1/31 [00:00<00:06,  4.80it/s]
  6%|▋         | 2/31 [00:00<00:05,  4.89it/s]
 10%|▉         | 3/31 [00:00<00:05,  4.92it/s]
 13%|█▎        | 4/31 [00:00<00:05,  4.94it/s]
 16%|█▌        | 5/31 [00:01<00:05,  4.95it/s]
 19%|█▉        | 6/31 [00:01<00:05,  4.95it/s]
 23%|██▎       | 7/31 [00:01<00:04,  4.97it/s]
 26%|██▌       | 8/31 [00:01<00:04,  4.97it/s]
 29%|██▉       | 9/31 [00:01<00:04,  4.98it/s]
 32%|███▏      | 10/31 [00:02<00:04,  4.98it/s]
 35%|███▌      | 11/31 [00:02<00:04,  4.97it/s]
 39%|███▊      | 12/31 [00:02<00:03,  4.98it/s]
 42%|████▏     | 13/31 [00:02<00:03,  4.98it/s]
 45%|████▌     | 14/31 [00:02<00:03,  4.99it/s]
 48%|████▊     | 15/31 [00:03<00:03,  4.98it/s]
 52%|█████▏    | 16/31 [00:03<00:03,  4.98it/s]
 55%|█████▍    | 17/31 [00:03<00:02,  4.98it/s]
 58%|█████▊    | 18/31 [00:03<00:02,  4.98it/s]
 61%|██████▏   | 19/31 [00:03<00:02,  4.98it/s]
 65%|██████▍   | 20/31 [00:04<00:02,  4.97it/s]
 68%|██████▊   | 21/31 [00:04<00:02,  4.98it/s]
 71%|███████   | 22/31 [00:04<00:01,  4.97it/s]
 74%|███████▍  | 23/31 [00:04<00:01,  4.97it/s]
 77%|███████▋  | 24/31 [00:04<00:01,  4.97it/s]
 81%|████████  | 25/31 [00:05<00:01,  4.97it/s]
 84%|████████▍ | 26/31 [00:05<00:01,  4.97it/s]
 87%|████████▋ | 27/31 [00:05<00:00,  4.97it/s]
 90%|█████████ | 28/31 [00:05<00:00,  4.97it/s]
 94%|█████████▎| 29/31 [00:05<00:00,  4.97it/s]
 97%|█████████▋| 30/31 [00:06<00:00,  4.97it/s]
100%|██████████| 31/31 [00:06<00:00,  4.97it/s]
100%|██████████| 31/31 [00:06<00:00,  4.97it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:00<00:02,  4.15it/s]
 20%|██        | 2/10 [00:00<00:01,  4.21it/s]
 30%|███       | 3/10 [00:00<00:01,  4.23it/s]
 40%|████      | 4/10 [00:00<00:01,  4.24it/s]
 50%|█████     | 5/10 [00:01<00:01,  4.24it/s]
 60%|██████    | 6/10 [00:01<00:00,  4.24it/s]
 70%|███████   | 7/10 [00:01<00:00,  4.24it/s]
 80%|████████  | 8/10 [00:01<00:00,  4.24it/s]
 90%|█████████ | 9/10 [00:02<00:00,  4.24it/s]
100%|██████████| 10/10 [00:02<00:00,  4.24it/s]
100%|██████████| 10/10 [00:02<00:00,  4.24it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:2f779eb9

vu42q7dbkm6iicbpal4v6uvbqm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

14.2s

Created

over 1 year ago by @stability-ai

Input

width: 1024
height: 1024
prompt: An astronaut riding a rainbow unicorn, cinematic, dramatic
refine: expert_ensemble_refiner
scheduler: DDIM
num_outputs: 1
guidance_scale: 7.5
high_noise_frac: 0.8
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
  "refine": "expert_ensemble_refiner",
  "scheduler": "DDIM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      refine: "expert_ensemble_refiner",
      scheduler: "DDIM",
      num_outputs: 1,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
        "refine": "expert_ensemble_refiner",
        "scheduler": "DDIM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      "refine": "expert_ensemble_refiner",
      "scheduler": "DDIM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "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.

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="An astronaut riding a rainbow unicorn, cinematic, dramatic"' \
  -i 'refine="expert_ensemble_refiner"' \
  -i 'scheduler="DDIM"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      "refine": "expert_ensemble_refiner",
      "scheduler": "DDIM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-26T21:04:37.933562Z",
  "created_at": "2023-07-26T21:04:23.762683Z",
  "data_removed": false,
  "error": null,
  "id": "vu42q7dbkm6iicbpal4v6uvbqm",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
    "refine": "expert_ensemble_refiner",
    "scheduler": "DDIM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 12103\ntxt2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:34,  1.14it/s]\n  5%|▌         | 2/40 [00:01<00:18,  2.10it/s]\n  8%|▊         | 3/40 [00:01<00:12,  2.86it/s]\n 10%|█         | 4/40 [00:01<00:10,  3.44it/s]\n 12%|█▎        | 5/40 [00:01<00:09,  3.87it/s]\n 15%|█▌        | 6/40 [00:01<00:08,  4.19it/s]\n 18%|█▊        | 7/40 [00:02<00:07,  4.43it/s]\n 20%|██        | 8/40 [00:02<00:06,  4.60it/s]\n 22%|██▎       | 9/40 [00:02<00:06,  4.72it/s]\n 25%|██▌       | 10/40 [00:02<00:06,  4.80it/s]\n 28%|██▊       | 11/40 [00:02<00:05,  4.86it/s]\n 30%|███       | 12/40 [00:03<00:05,  4.90it/s]\n 32%|███▎      | 13/40 [00:03<00:05,  4.93it/s]\n 35%|███▌      | 14/40 [00:03<00:05,  4.95it/s]\n 38%|███▊      | 15/40 [00:03<00:05,  4.97it/s]\n 40%|████      | 16/40 [00:03<00:04,  4.99it/s]\n 42%|████▎     | 17/40 [00:04<00:04,  5.00it/s]\n 45%|████▌     | 18/40 [00:04<00:04,  5.02it/s]\n 48%|████▊     | 19/40 [00:04<00:04,  5.02it/s]\n 50%|█████     | 20/40 [00:04<00:03,  5.03it/s]\n 52%|█████▎    | 21/40 [00:04<00:03,  5.03it/s]\n 55%|█████▌    | 22/40 [00:05<00:03,  5.03it/s]\n 57%|█████▊    | 23/40 [00:05<00:03,  5.03it/s]\n 60%|██████    | 24/40 [00:05<00:03,  5.04it/s]\n 62%|██████▎   | 25/40 [00:05<00:02,  5.05it/s]\n 65%|██████▌   | 26/40 [00:05<00:02,  5.04it/s]\n 68%|██████▊   | 27/40 [00:06<00:02,  5.03it/s]\n 70%|███████   | 28/40 [00:06<00:02,  5.03it/s]\n 72%|███████▎  | 29/40 [00:06<00:02,  5.03it/s]\n 75%|███████▌  | 30/40 [00:06<00:01,  5.04it/s]\n 78%|███████▊  | 31/40 [00:06<00:01,  5.03it/s]\n 80%|████████  | 32/40 [00:07<00:01,  5.02it/s]\n 82%|████████▎ | 33/40 [00:07<00:01,  5.02it/s]\n 85%|████████▌ | 34/40 [00:07<00:01,  5.02it/s]\n 88%|████████▊ | 35/40 [00:07<00:00,  5.03it/s]\n 90%|█████████ | 36/40 [00:07<00:00,  5.03it/s]\n 92%|█████████▎| 37/40 [00:08<00:00,  5.02it/s]\n 95%|█████████▌| 38/40 [00:08<00:00,  5.02it/s]\n 98%|█████████▊| 39/40 [00:08<00:00,  5.02it/s]\n100%|██████████| 40/40 [00:08<00:00,  5.02it/s]\n100%|██████████| 40/40 [00:08<00:00,  4.63it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:02,  4.24it/s]\n 20%|██        | 2/10 [00:00<00:01,  4.33it/s]\n 30%|███       | 3/10 [00:00<00:01,  4.36it/s]\n 40%|████      | 4/10 [00:00<00:01,  4.37it/s]\n 50%|█████     | 5/10 [00:01<00:01,  4.37it/s]\n 60%|██████    | 6/10 [00:01<00:00,  4.38it/s]\n 70%|███████   | 7/10 [00:01<00:00,  4.38it/s]\n 80%|████████  | 8/10 [00:01<00:00,  4.39it/s]\n 90%|█████████ | 9/10 [00:02<00:00,  4.37it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.37it/s]\n100%|██████████| 10/10 [00:02<00:00,  4.37it/s]",
  "metrics": {
    "predict_time": 14.149563,
    "total_time": 14.170879
  },
  "output": [
    "https://replicate.delivery/pbxt/E6Ftpfi0dF1SOi4b6ltUwsfdxUf7zTQSfdhmJfRcfGTdZ88UE/out-0.png"
  ],
  "started_at": "2023-07-26T21:04:23.783999Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/vu42q7dbkm6iicbpal4v6uvbqm",
    "cancel": "https://api.replicate.com/v1/predictions/vu42q7dbkm6iicbpal4v6uvbqm/cancel"
  },
  "version": "2f779eb9b23b34fe171f8eaa021b8261566f0d2c10cd2674063e7dbcd351509e"
}

Generated in

14.2 seconds

Tweak it ShareReport

Using seed: 12103
txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:34,  1.14it/s]
  5%|▌         | 2/40 [00:01<00:18,  2.10it/s]
  8%|▊         | 3/40 [00:01<00:12,  2.86it/s]
 10%|█         | 4/40 [00:01<00:10,  3.44it/s]
 12%|█▎        | 5/40 [00:01<00:09,  3.87it/s]
 15%|█▌        | 6/40 [00:01<00:08,  4.19it/s]
 18%|█▊        | 7/40 [00:02<00:07,  4.43it/s]
 20%|██        | 8/40 [00:02<00:06,  4.60it/s]
 22%|██▎       | 9/40 [00:02<00:06,  4.72it/s]
 25%|██▌       | 10/40 [00:02<00:06,  4.80it/s]
 28%|██▊       | 11/40 [00:02<00:05,  4.86it/s]
 30%|███       | 12/40 [00:03<00:05,  4.90it/s]
 32%|███▎      | 13/40 [00:03<00:05,  4.93it/s]
 35%|███▌      | 14/40 [00:03<00:05,  4.95it/s]
 38%|███▊      | 15/40 [00:03<00:05,  4.97it/s]
 40%|████      | 16/40 [00:03<00:04,  4.99it/s]
 42%|████▎     | 17/40 [00:04<00:04,  5.00it/s]
 45%|████▌     | 18/40 [00:04<00:04,  5.02it/s]
 48%|████▊     | 19/40 [00:04<00:04,  5.02it/s]
 50%|█████     | 20/40 [00:04<00:03,  5.03it/s]
 52%|█████▎    | 21/40 [00:04<00:03,  5.03it/s]
 55%|█████▌    | 22/40 [00:05<00:03,  5.03it/s]
 57%|█████▊    | 23/40 [00:05<00:03,  5.03it/s]
 60%|██████    | 24/40 [00:05<00:03,  5.04it/s]
 62%|██████▎   | 25/40 [00:05<00:02,  5.05it/s]
 65%|██████▌   | 26/40 [00:05<00:02,  5.04it/s]
 68%|██████▊   | 27/40 [00:06<00:02,  5.03it/s]
 70%|███████   | 28/40 [00:06<00:02,  5.03it/s]
 72%|███████▎  | 29/40 [00:06<00:02,  5.03it/s]
 75%|███████▌  | 30/40 [00:06<00:01,  5.04it/s]
 78%|███████▊  | 31/40 [00:06<00:01,  5.03it/s]
 80%|████████  | 32/40 [00:07<00:01,  5.02it/s]
 82%|████████▎ | 33/40 [00:07<00:01,  5.02it/s]
 85%|████████▌ | 34/40 [00:07<00:01,  5.02it/s]
 88%|████████▊ | 35/40 [00:07<00:00,  5.03it/s]
 90%|█████████ | 36/40 [00:07<00:00,  5.03it/s]
 92%|█████████▎| 37/40 [00:08<00:00,  5.02it/s]
 95%|█████████▌| 38/40 [00:08<00:00,  5.02it/s]
 98%|█████████▊| 39/40 [00:08<00:00,  5.02it/s]
100%|██████████| 40/40 [00:08<00:00,  5.02it/s]
100%|██████████| 40/40 [00:08<00:00,  4.63it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:00<00:02,  4.24it/s]
 20%|██        | 2/10 [00:00<00:01,  4.33it/s]
 30%|███       | 3/10 [00:00<00:01,  4.36it/s]
 40%|████      | 4/10 [00:00<00:01,  4.37it/s]
 50%|█████     | 5/10 [00:01<00:01,  4.37it/s]
 60%|██████    | 6/10 [00:01<00:00,  4.38it/s]
 70%|███████   | 7/10 [00:01<00:00,  4.38it/s]
 80%|████████  | 8/10 [00:01<00:00,  4.39it/s]
 90%|█████████ | 9/10 [00:02<00:00,  4.37it/s]
100%|██████████| 10/10 [00:02<00:00,  4.37it/s]
100%|██████████| 10/10 [00:02<00:00,  4.37it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:2b017d9b

z4x5jkdbsnoceeuwmk5lka57uu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

16.5s

Created

over 1 year ago by @stability-ai

Input

mask
seed: 46099
image
width: 1024
height: 1024
prompt: A rainbow coloured bear
refine: base_image_refiner
scheduler: KarrasDPM
num_outputs: 1
refine_steps: 50
guidance_scale: 7.5
high_noise_frac: 0.8
prompt_strength: 0.95
num_inference_steps: 50

{
  "mask": "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
  "seed": 46099,
  "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
  "width": 1024,
  "height": 1024,
  "prompt": "A rainbow coloured bear",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "refine_steps": 50,
  "guidance_scale": 7.5,
  "high_noise_frac": 0.8,
  "prompt_strength": 0.95,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
      seed: 46099,
      image: "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      width: 1024,
      height: 1024,
      prompt: "A rainbow coloured bear",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      refine_steps: 50,
      guidance_scale: 7.5,
      high_noise_frac: 0.8,
      prompt_strength: 0.95,
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "mask": "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
        "seed": 46099,
        "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
        "width": 1024,
        "height": 1024,
        "prompt": "A rainbow coloured bear",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "refine_steps": 50,
        "guidance_scale": 7.5,
        "high_noise_frac": 0.8,
        "prompt_strength": 0.95,
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "mask": "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
      "seed": 46099,
      "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      "width": 1024,
      "height": 1024,
      "prompt": "A rainbow coloured bear",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "refine_steps": 50,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.95,
      "num_inference_steps": 50
    }
  }' \
  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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'mask="https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png"' \
  -i 'seed=46099' \
  -i 'image="https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A rainbow coloured bear"' \
  -i 'refine="base_image_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'num_outputs=1' \
  -i 'refine_steps=50' \
  -i 'guidance_scale=7.5' \
  -i 'high_noise_frac=0.8' \
  -i 'prompt_strength=0.95' \
  -i 'num_inference_steps=50'

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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "mask": "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
      "seed": 46099,
      "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
      "width": 1024,
      "height": 1024,
      "prompt": "A rainbow coloured bear",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "refine_steps": 50,
      "guidance_scale": 7.5,
      "high_noise_frac": 0.8,
      "prompt_strength": 0.95,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-07-27T12:36:29.921311Z",
  "created_at": "2023-07-27T12:36:13.439420Z",
  "data_removed": false,
  "error": null,
  "id": "z4x5jkdbsnoceeuwmk5lka57uu",
  "input": {
    "mask": "https://replicate.delivery/pbxt/JFIZFfJsSnWgxbTmEYLqhHIGdZo9o2BX3p47wSdn55HWtMON/mask1.png",
    "seed": 46099,
    "image": "https://replicate.delivery/pbxt/JF3foGR90vm9BXSEXNaYkaeVKHYbJPinmpbMFvRtlDpH4MMk/out-0-1.png",
    "width": 1024,
    "height": 1024,
    "prompt": "A rainbow coloured bear",
    "refine": "base_image_refiner",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "refine_steps": 50,
    "guidance_scale": 7.5,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.95,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 46099\ninpainting mode\n  0%|          | 0/47 [00:00<?, ?it/s]\n  2%|▏         | 1/47 [00:00<00:09,  4.96it/s]\n  4%|▍         | 2/47 [00:00<00:09,  4.95it/s]\n  6%|▋         | 3/47 [00:00<00:08,  4.94it/s]\n  9%|▊         | 4/47 [00:00<00:08,  4.94it/s]\n 11%|█         | 5/47 [00:01<00:08,  4.93it/s]\n 13%|█▎        | 6/47 [00:01<00:08,  4.93it/s]\n 15%|█▍        | 7/47 [00:01<00:08,  4.93it/s]\n 17%|█▋        | 8/47 [00:01<00:07,  4.92it/s]\n 19%|█▉        | 9/47 [00:01<00:07,  4.92it/s]\n 21%|██▏       | 10/47 [00:02<00:07,  4.91it/s]\n 23%|██▎       | 11/47 [00:02<00:07,  4.91it/s]\n 26%|██▌       | 12/47 [00:02<00:07,  4.92it/s]\n 28%|██▊       | 13/47 [00:02<00:06,  4.92it/s]\n 30%|██▉       | 14/47 [00:02<00:06,  4.91it/s]\n 32%|███▏      | 15/47 [00:03<00:06,  4.90it/s]\n 34%|███▍      | 16/47 [00:03<00:06,  4.90it/s]\n 36%|███▌      | 17/47 [00:03<00:06,  4.91it/s]\n 38%|███▊      | 18/47 [00:03<00:05,  4.90it/s]\n 40%|████      | 19/47 [00:03<00:05,  4.90it/s]\n 43%|████▎     | 20/47 [00:04<00:05,  4.90it/s]\n 45%|████▍     | 21/47 [00:04<00:05,  4.90it/s]\n 47%|████▋     | 22/47 [00:04<00:05,  4.90it/s]\n 49%|████▉     | 23/47 [00:04<00:04,  4.90it/s]\n 51%|█████     | 24/47 [00:04<00:04,  4.90it/s]\n 53%|█████▎    | 25/47 [00:05<00:04,  4.90it/s]\n 55%|█████▌    | 26/47 [00:05<00:04,  4.90it/s]\n 57%|█████▋    | 27/47 [00:05<00:04,  4.90it/s]\n 60%|█████▉    | 28/47 [00:05<00:03,  4.90it/s]\n 62%|██████▏   | 29/47 [00:05<00:03,  4.89it/s]\n 64%|██████▍   | 30/47 [00:06<00:03,  4.89it/s]\n 66%|██████▌   | 31/47 [00:06<00:03,  4.89it/s]\n 68%|██████▊   | 32/47 [00:06<00:03,  4.89it/s]\n 70%|███████   | 33/47 [00:06<00:02,  4.89it/s]\n 72%|███████▏  | 34/47 [00:06<00:02,  4.89it/s]\n 74%|███████▍  | 35/47 [00:07<00:02,  4.89it/s]\n 77%|███████▋  | 36/47 [00:07<00:02,  4.90it/s]\n 79%|███████▊  | 37/47 [00:07<00:02,  4.91it/s]\n 81%|████████  | 38/47 [00:07<00:01,  4.91it/s]\n 83%|████████▎ | 39/47 [00:07<00:01,  4.92it/s]\n 85%|████████▌ | 40/47 [00:08<00:01,  4.92it/s]\n 87%|████████▋ | 41/47 [00:08<00:01,  4.91it/s]\n 89%|████████▉ | 42/47 [00:08<00:01,  4.86it/s]\n 91%|█████████▏| 43/47 [00:08<00:00,  4.87it/s]\n 94%|█████████▎| 44/47 [00:08<00:00,  4.89it/s]\n 96%|█████████▌| 45/47 [00:09<00:00,  4.91it/s]\n98%|█████████▊| 46/47 [00:09<00:00,  4.92it/s]\n98%|█████████▊| 46/47 [00:09<00:00,  4.91it/s]\n  0%|          | 0/15 [00:00<?, ?it/s]\n  7%|▋         | 1/15 [00:00<00:03,  4.33it/s]\n 13%|█▎        | 2/15 [00:00<00:03,  4.32it/s]\n 20%|██        | 3/15 [00:00<00:02,  4.32it/s]\n 27%|██▋       | 4/15 [00:00<00:02,  4.31it/s]\n 33%|███▎      | 5/15 [00:01<00:02,  4.31it/s]\n 40%|████      | 6/15 [00:01<00:02,  4.31it/s]\n 47%|████▋     | 7/15 [00:01<00:01,  4.31it/s]\n 53%|█████▎    | 8/15 [00:01<00:01,  4.31it/s]\n 60%|██████    | 9/15 [00:02<00:01,  4.30it/s]\n 67%|██████▋   | 10/15 [00:02<00:01,  4.30it/s]\n 73%|███████▎  | 11/15 [00:02<00:00,  4.30it/s]\n 80%|████████  | 12/15 [00:02<00:00,  4.30it/s]\n 87%|████████▋ | 13/15 [00:03<00:00,  4.30it/s]\n 93%|█████████▎| 14/15 [00:03<00:00,  4.31it/s]\n100%|██████████| 15/15 [00:03<00:00,  4.31it/s]\n100%|██████████| 15/15 [00:03<00:00,  4.31it/s]",
  "metrics": {
    "predict_time": 16.506152,
    "total_time": 16.481891
  },
  "output": [
    "https://replicate.delivery/pbxt/NfV2n6S8wBVRekodJQ6QObMKAS5ntznisaIaAi3fVlIY2CoiA/out-0.png"
  ],
  "started_at": "2023-07-27T12:36:13.415159Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/z4x5jkdbsnoceeuwmk5lka57uu",
    "cancel": "https://api.replicate.com/v1/predictions/z4x5jkdbsnoceeuwmk5lka57uu/cancel"
  },
  "version": "2b017d9b67edd2ee1401238df49d75da53c523f36e363881e057f5dc3ed3c5b2"
}

Generated in

16.5 seconds

Tweak it ShareReport

Using seed: 46099
inpainting mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:00<00:09,  4.96it/s]
  4%|▍         | 2/47 [00:00<00:09,  4.95it/s]
  6%|▋         | 3/47 [00:00<00:08,  4.94it/s]
  9%|▊         | 4/47 [00:00<00:08,  4.94it/s]
 11%|█         | 5/47 [00:01<00:08,  4.93it/s]
 13%|█▎        | 6/47 [00:01<00:08,  4.93it/s]
 15%|█▍        | 7/47 [00:01<00:08,  4.93it/s]
 17%|█▋        | 8/47 [00:01<00:07,  4.92it/s]
 19%|█▉        | 9/47 [00:01<00:07,  4.92it/s]
 21%|██▏       | 10/47 [00:02<00:07,  4.91it/s]
 23%|██▎       | 11/47 [00:02<00:07,  4.91it/s]
 26%|██▌       | 12/47 [00:02<00:07,  4.92it/s]
 28%|██▊       | 13/47 [00:02<00:06,  4.92it/s]
 30%|██▉       | 14/47 [00:02<00:06,  4.91it/s]
 32%|███▏      | 15/47 [00:03<00:06,  4.90it/s]
 34%|███▍      | 16/47 [00:03<00:06,  4.90it/s]
 36%|███▌      | 17/47 [00:03<00:06,  4.91it/s]
 38%|███▊      | 18/47 [00:03<00:05,  4.90it/s]
 40%|████      | 19/47 [00:03<00:05,  4.90it/s]
 43%|████▎     | 20/47 [00:04<00:05,  4.90it/s]
 45%|████▍     | 21/47 [00:04<00:05,  4.90it/s]
 47%|████▋     | 22/47 [00:04<00:05,  4.90it/s]
 49%|████▉     | 23/47 [00:04<00:04,  4.90it/s]
 51%|█████     | 24/47 [00:04<00:04,  4.90it/s]
 53%|█████▎    | 25/47 [00:05<00:04,  4.90it/s]
 55%|█████▌    | 26/47 [00:05<00:04,  4.90it/s]
 57%|█████▋    | 27/47 [00:05<00:04,  4.90it/s]
 60%|█████▉    | 28/47 [00:05<00:03,  4.90it/s]
 62%|██████▏   | 29/47 [00:05<00:03,  4.89it/s]
 64%|██████▍   | 30/47 [00:06<00:03,  4.89it/s]
 66%|██████▌   | 31/47 [00:06<00:03,  4.89it/s]
 68%|██████▊   | 32/47 [00:06<00:03,  4.89it/s]
 70%|███████   | 33/47 [00:06<00:02,  4.89it/s]
 72%|███████▏  | 34/47 [00:06<00:02,  4.89it/s]
 74%|███████▍  | 35/47 [00:07<00:02,  4.89it/s]
 77%|███████▋  | 36/47 [00:07<00:02,  4.90it/s]
 79%|███████▊  | 37/47 [00:07<00:02,  4.91it/s]
 81%|████████  | 38/47 [00:07<00:01,  4.91it/s]
 83%|████████▎ | 39/47 [00:07<00:01,  4.92it/s]
 85%|████████▌ | 40/47 [00:08<00:01,  4.92it/s]
 87%|████████▋ | 41/47 [00:08<00:01,  4.91it/s]
 89%|████████▉ | 42/47 [00:08<00:01,  4.86it/s]
 91%|█████████▏| 43/47 [00:08<00:00,  4.87it/s]
 94%|█████████▎| 44/47 [00:08<00:00,  4.89it/s]
 96%|█████████▌| 45/47 [00:09<00:00,  4.91it/s]
98%|█████████▊| 46/47 [00:09<00:00,  4.92it/s]
98%|█████████▊| 46/47 [00:09<00:00,  4.91it/s]
  0%|          | 0/15 [00:00<?, ?it/s]
  7%|▋         | 1/15 [00:00<00:03,  4.33it/s]
 13%|█▎        | 2/15 [00:00<00:03,  4.32it/s]
 20%|██        | 3/15 [00:00<00:02,  4.32it/s]
 27%|██▋       | 4/15 [00:00<00:02,  4.31it/s]
 33%|███▎      | 5/15 [00:01<00:02,  4.31it/s]
 40%|████      | 6/15 [00:01<00:02,  4.31it/s]
 47%|████▋     | 7/15 [00:01<00:01,  4.31it/s]
 53%|█████▎    | 8/15 [00:01<00:01,  4.31it/s]
 60%|██████    | 9/15 [00:02<00:01,  4.30it/s]
 67%|██████▋   | 10/15 [00:02<00:01,  4.30it/s]
 73%|███████▎  | 11/15 [00:02<00:00,  4.30it/s]
 80%|████████  | 12/15 [00:02<00:00,  4.30it/s]
 87%|████████▋ | 13/15 [00:03<00:00,  4.30it/s]
 93%|█████████▎| 14/15 [00:03<00:00,  4.31it/s]
100%|██████████| 15/15 [00:03<00:00,  4.31it/s]
100%|██████████| 15/15 [00:03<00:00,  4.31it/s]

Prediction

stability-ai/sdxl:7762fd07

Model

stability-ai/sdxl:c221b2b8

dzsqmb3bg4lqpjkz2iptjqgccm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

5.0s

Created

over 1 year ago by @fofr

Input

width: 768
height: 768
prompt: An astronaut riding a rainbow unicorn, cinematic, dramatic
refine: expert_ensemble_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 25

{
  "width": 768,
  "height": 768,
  "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}

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

const output = await replicate.run(
  "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
  {
    input: {
      width: 768,
      height: 768,
      prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "",
      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 stability-ai/sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    input={
        "width": 768,
        "height": 768,
        "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "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 stability-ai/sdxl 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": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc \
  -i 'width=768' \
  -i 'height=768' \
  -i 'prompt="An astronaut riding a rainbow unicorn, cinematic, dramatic"' \
  -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=0.8' \
  -i 'negative_prompt=""' \
  -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/stability-ai/sdxl@sha256:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "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": "2023-10-12T17:10:12.909279Z",
  "created_at": "2023-10-12T17:10:07.956869Z",
  "data_removed": false,
  "error": null,
  "id": "dzsqmb3bg4lqpjkz2iptjqgccm",
  "input": {
    "width": 768,
    "height": 768,
    "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
    "refine": "expert_ensemble_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": false,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 25
  },
  "logs": "Using seed: 16010\nPrompt: An astronaut riding a rainbow unicorn, cinematic, dramatic\ntxt2img mode\n  0%|          | 0/16 [00:00<?, ?it/s]\n  6%|▋         | 1/16 [00:00<00:01,  7.96it/s]\n 12%|█▎        | 2/16 [00:00<00:01,  7.89it/s]\n 19%|█▉        | 3/16 [00:00<00:01,  7.86it/s]\n 25%|██▌       | 4/16 [00:00<00:01,  7.85it/s]\n 31%|███▏      | 5/16 [00:00<00:01,  7.83it/s]\n 38%|███▊      | 6/16 [00:00<00:01,  7.82it/s]\n 44%|████▍     | 7/16 [00:00<00:01,  7.81it/s]\n 50%|█████     | 8/16 [00:01<00:01,  7.80it/s]\n 56%|█████▋    | 9/16 [00:01<00:00,  7.80it/s]\n 62%|██████▎   | 10/16 [00:01<00:00,  7.78it/s]\n 69%|██████▉   | 11/16 [00:01<00:00,  7.79it/s]\n 75%|███████▌  | 12/16 [00:01<00:00,  7.79it/s]\n 81%|████████▏ | 13/16 [00:01<00:00,  7.78it/s]\n 88%|████████▊ | 14/16 [00:01<00:00,  7.79it/s]\n 94%|█████████▍| 15/16 [00:01<00:00,  7.79it/s]\n100%|██████████| 16/16 [00:02<00:00,  7.79it/s]\n100%|██████████| 16/16 [00:02<00:00,  7.81it/s]\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:00<00:00,  7.47it/s]\n 40%|████      | 2/5 [00:00<00:00,  7.42it/s]\n 60%|██████    | 3/5 [00:00<00:00,  7.40it/s]\n 80%|████████  | 4/5 [00:00<00:00,  7.39it/s]\n100%|██████████| 5/5 [00:00<00:00,  7.39it/s]\n100%|██████████| 5/5 [00:00<00:00,  7.40it/s]",
  "metrics": {
    "predict_time": 4.981337,
    "total_time": 4.95241
  },
  "output": [
    "https://pbxt.replicate.delivery/YXbcLudoHBIYHV6L0HbcTx5iRzLFMwygLr3vhGpZI35caXbE/out-0.png"
  ],
  "started_at": "2023-10-12T17:10:07.927942Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/dzsqmb3bg4lqpjkz2iptjqgccm",
    "cancel": "https://api.replicate.com/v1/predictions/dzsqmb3bg4lqpjkz2iptjqgccm/cancel"
  },
  "version": "c221b2b8ef527988fb59bf24a8b97c4561f1c671f73bd389f866bfb27c061316"
}

Generated in

5.0 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model

stability-ai / sdxl

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (zuv3yw3bis3kvmypxkefqlowme)

Logs (faz67o3bvxmrr5ydw7yhustwfq)

Logs (54q24ulbyhpgb3gmbs2yryboa4)

Logs (wv7kgx3bgsguc3cnltku6me4py)

Logs (ks4e2jdb6zef4xodz3mz5utuu4)

Logs (lrmn5btbq2o5xpbksl56fw4y64)

Logs (vu42q7dbkm6iicbpal4v6uvbqm)

Logs (z4x5jkdbsnoceeuwmk5lka57uu)

Logs (dzsqmb3bg4lqpjkz2iptjqgccm)