lucataco / pasd-magnify

image
prompt: Frog, clean, high-resolution, 8k, best quality, masterpiece
n_prompt: dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
denoise_steps: 20
guidance_scale: 7.5
upsample_scale: 2
conditioning_scale: 1.1

{
  "image": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
  "prompt": "Frog, clean, high-resolution, 8k, best quality, masterpiece",
  "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "denoise_steps": 20,
  "guidance_scale": 7.5,
  "upsample_scale": 2,
  "conditioning_scale": 1.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
      prompt: "Frog, clean, high-resolution, 8k, best quality, masterpiece",
      n_prompt: "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      denoise_steps: 20,
      guidance_scale: 7.5,
      upsample_scale: 2,
      conditioning_scale: 1.1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    input={
        "image": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
        "prompt": "Frog, clean, high-resolution, 8k, best quality, masterpiece",
        "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "denoise_steps": 20,
        "guidance_scale": 7.5,
        "upsample_scale": 2,
        "conditioning_scale": 1.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/pasd-magnify 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": "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    "input": {
      "image": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
      "prompt": "Frog, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195 \
  -i 'image="https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png"' \
  -i 'prompt="Frog, clean, high-resolution, 8k, best quality, masterpiece"' \
  -i 'n_prompt="dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"' \
  -i 'denoise_steps=20' \
  -i 'guidance_scale=7.5' \
  -i 'upsample_scale=2' \
  -i 'conditioning_scale=1.1'

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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
      "prompt": "Frog, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  http://localhost:5000/predictions

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

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
  "outut": "https://replicate.delivery/pbxt/MGJy2aTpJB7dI1sQ49nfZpdQh2pesLIF6cC22ySbGo0LhcKSA/output-20240108153527.jpg"
}

{
  "completed_at": "2024-01-08T15:35:40.256846Z",
  "created_at": "2024-01-08T15:33:16.794743Z",
  "data_removed": false,
  "error": null,
  "id": "wo45dqtbfv6zj3pwqldqj3qbxe",
  "input": {
    "image": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
    "prompt": "Frog, clean, high-resolution, 8k, best quality, masterpiece",
    "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "denoise_steps": 20,
    "guidance_scale": 7.5,
    "upsample_scale": 2,
    "conditioning_scale": 1.1
  },
  "logs": "Using seed: 2896644955\nSeed set to 2896644955\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:12,  1.54it/s]\n 10%|█         | 2/20 [00:01<00:10,  1.76it/s]\n 15%|█▌        | 3/20 [00:01<00:09,  1.82it/s]\n 20%|██        | 4/20 [00:02<00:08,  1.86it/s]\n 25%|██▌       | 5/20 [00:02<00:07,  1.89it/s]\n 30%|███       | 6/20 [00:03<00:07,  1.90it/s]\n 35%|███▌      | 7/20 [00:03<00:06,  1.91it/s]\n 40%|████      | 8/20 [00:04<00:06,  1.91it/s]\n 45%|████▌     | 9/20 [00:04<00:05,  1.92it/s]\n 50%|█████     | 10/20 [00:05<00:05,  1.92it/s]\n 55%|█████▌    | 11/20 [00:05<00:04,  1.92it/s]\n 60%|██████    | 12/20 [00:06<00:04,  1.92it/s]\n 65%|██████▌   | 13/20 [00:06<00:03,  1.92it/s]\n 70%|███████   | 14/20 [00:07<00:03,  1.92it/s]\n 75%|███████▌  | 15/20 [00:07<00:02,  1.93it/s]\n 80%|████████  | 16/20 [00:08<00:02,  1.93it/s]\n 85%|████████▌ | 17/20 [00:08<00:01,  1.93it/s]\n 90%|█████████ | 18/20 [00:09<00:01,  1.93it/s]\n 95%|█████████▌| 19/20 [00:09<00:00,  1.93it/s]\n100%|██████████| 20/20 [00:10<00:00,  1.93it/s]\n100%|██████████| 20/20 [00:10<00:00,  1.90it/s]\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\n[Tiled VAE]: Done in 11.102s, max VRAM alloc 5803.197 MB",
  "metrics": {
    "predict_time": 13.316808,
    "total_time": 143.462103
  },
  "output": "https://replicate.delivery/pbxt/MGJy2aTpJB7dI1sQ49nfZpdQh2pesLIF6cC22ySbGo0LhcKSA/output-20240108153527.jpg",
  "started_at": "2024-01-08T15:35:26.940038Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wo45dqtbfv6zj3pwqldqj3qbxe",
    "cancel": "https://api.replicate.com/v1/predictions/wo45dqtbfv6zj3pwqldqj3qbxe/cancel"
  },
  "version": "d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195"
}

Generated in

13.3 seconds

Tweak it ShareReport

Prediction

lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195

Model

lucataco/pasd-magnify:d59e83ee

nlirdh3buafwtelxm65fhlg6pu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

25.8s

Created

over 1 year ago

Input

image
prompt: house, clean, high-resolution, 8k, best quality, masterpiece
n_prompt: dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
denoise_steps: 20
guidance_scale: 7.5
upsample_scale: 2
conditioning_scale: 1.1

{
  "image": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
  "prompt": "house, clean, high-resolution, 8k, best quality, masterpiece",
  "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "denoise_steps": 20,
  "guidance_scale": 7.5,
  "upsample_scale": 2,
  "conditioning_scale": 1.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
      prompt: "house, clean, high-resolution, 8k, best quality, masterpiece",
      n_prompt: "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      denoise_steps: 20,
      guidance_scale: 7.5,
      upsample_scale: 2,
      conditioning_scale: 1.1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    input={
        "image": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
        "prompt": "house, clean, high-resolution, 8k, best quality, masterpiece",
        "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "denoise_steps": 20,
        "guidance_scale": 7.5,
        "upsample_scale": 2,
        "conditioning_scale": 1.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/pasd-magnify 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": "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    "input": {
      "image": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
      "prompt": "house, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195 \
  -i 'image="https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg"' \
  -i 'prompt="house, clean, high-resolution, 8k, best quality, masterpiece"' \
  -i 'n_prompt="dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"' \
  -i 'denoise_steps=20' \
  -i 'guidance_scale=7.5' \
  -i 'upsample_scale=2' \
  -i 'conditioning_scale=1.1'

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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
      "prompt": "house, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  http://localhost:5000/predictions

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

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
  "outut": "https://replicate.delivery/pbxt/pjZeMiqjdXwKRKKiJJrsOuNYcSMSmt5VA7JZZGV621zcjOFJA/output-20240108161528.jpg"
}

{
  "completed_at": "2024-01-08T16:15:54.119289Z",
  "created_at": "2024-01-08T16:15:28.327054Z",
  "data_removed": false,
  "error": null,
  "id": "nlirdh3buafwtelxm65fhlg6pu",
  "input": {
    "image": "https://replicate.delivery/pbxt/KBv8fvMNUNpKA0UIeRmZO4vFTLLyACC5jShNNuZPualwMdEx/house.jpg",
    "prompt": "house, clean, high-resolution, 8k, best quality, masterpiece",
    "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "denoise_steps": 20,
    "guidance_scale": 7.5,
    "upsample_scale": 2,
    "conditioning_scale": 1.1
  },
  "logs": "Using seed: 3968342168\nSeed set to 3968342168\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:01<00:22,  1.16s/it]\n 10%|█         | 2/20 [00:02<00:20,  1.15s/it]\n 15%|█▌        | 3/20 [00:03<00:19,  1.14s/it]\n 20%|██        | 4/20 [00:04<00:18,  1.14s/it]\n 25%|██▌       | 5/20 [00:05<00:17,  1.14s/it]\n 30%|███       | 6/20 [00:06<00:15,  1.14s/it]\n 35%|███▌      | 7/20 [00:07<00:14,  1.14s/it]\n 40%|████      | 8/20 [00:09<00:13,  1.14s/it]\n 45%|████▌     | 9/20 [00:10<00:12,  1.14s/it]\n 50%|█████     | 10/20 [00:11<00:11,  1.14s/it]\n 55%|█████▌    | 11/20 [00:12<00:10,  1.14s/it]\n 60%|██████    | 12/20 [00:13<00:09,  1.14s/it]\n 65%|██████▌   | 13/20 [00:14<00:08,  1.14s/it]\n 70%|███████   | 14/20 [00:16<00:06,  1.15s/it]\n 75%|███████▌  | 15/20 [00:17<00:05,  1.15s/it]\n 80%|████████  | 16/20 [00:18<00:04,  1.15s/it]\n 85%|████████▌ | 17/20 [00:19<00:03,  1.15s/it]\n 90%|█████████ | 18/20 [00:20<00:02,  1.15s/it]\n 95%|█████████▌| 19/20 [00:21<00:01,  1.15s/it]\n100%|██████████| 20/20 [00:22<00:00,  1.15s/it]\n100%|██████████| 20/20 [00:22<00:00,  1.14s/it]\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\n[Tiled VAE]: Done in 23.650s, max VRAM alloc 7078.416 MB",
  "metrics": {
    "predict_time": 25.715897,
    "total_time": 25.792235
  },
  "output": "https://replicate.delivery/pbxt/pjZeMiqjdXwKRKKiJJrsOuNYcSMSmt5VA7JZZGV621zcjOFJA/output-20240108161528.jpg",
  "started_at": "2024-01-08T16:15:28.403392Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nlirdh3buafwtelxm65fhlg6pu",
    "cancel": "https://api.replicate.com/v1/predictions/nlirdh3buafwtelxm65fhlg6pu/cancel"
  },
  "version": "d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195"
}

Generated in

25.7 seconds

Tweak it ShareReport

Prediction

lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195

Model

lucataco/pasd-magnify:d59e83ee

wg4cdq3bd5dpmfglu7qjhe5zlq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.8s

Created

over 1 year ago

Input

image
prompt: woman, clean, high-resolution, 8k, best quality, masterpiece
n_prompt: dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
denoise_steps: 20
guidance_scale: 7.5
upsample_scale: 2
conditioning_scale: 1.1

{
  "image": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
  "prompt": "woman, clean, high-resolution, 8k, best quality, masterpiece",
  "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "denoise_steps": 20,
  "guidance_scale": 7.5,
  "upsample_scale": 2,
  "conditioning_scale": 1.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
      prompt: "woman, clean, high-resolution, 8k, best quality, masterpiece",
      n_prompt: "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      denoise_steps: 20,
      guidance_scale: 7.5,
      upsample_scale: 2,
      conditioning_scale: 1.1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    input={
        "image": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
        "prompt": "woman, clean, high-resolution, 8k, best quality, masterpiece",
        "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "denoise_steps": 20,
        "guidance_scale": 7.5,
        "upsample_scale": 2,
        "conditioning_scale": 1.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/pasd-magnify 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": "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    "input": {
      "image": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
      "prompt": "woman, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195 \
  -i 'image="https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png"' \
  -i 'prompt="woman, clean, high-resolution, 8k, best quality, masterpiece"' \
  -i 'n_prompt="dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"' \
  -i 'denoise_steps=20' \
  -i 'guidance_scale=7.5' \
  -i 'upsample_scale=2' \
  -i 'conditioning_scale=1.1'

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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
      "prompt": "woman, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  http://localhost:5000/predictions

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

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
  "outut": "https://replicate.delivery/pbxt/XhtUIywTlO6tLtEjK5fFYkkqx65YXWmt6jEdSZrJ7ZgBkOFJA/output-20240108161700.jpg"
}

{
  "completed_at": "2024-01-08T16:17:08.529298Z",
  "created_at": "2024-01-08T16:16:59.765058Z",
  "data_removed": false,
  "error": null,
  "id": "wg4cdq3bd5dpmfglu7qjhe5zlq",
  "input": {
    "image": "https://replicate.delivery/pbxt/KBvA8L0P34OamIkycl2GKIMTX9XqB88JietvBLeWxSD7tPbz/629e4da70703193b.png",
    "prompt": "woman, clean, high-resolution, 8k, best quality, masterpiece",
    "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "denoise_steps": 20,
    "guidance_scale": 7.5,
    "upsample_scale": 2,
    "conditioning_scale": 1.1
  },
  "logs": "Using seed: 3853534869\nSeed set to 3853534869\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:06,  2.96it/s]\n 10%|█         | 2/20 [00:00<00:05,  3.11it/s]\n 15%|█▌        | 3/20 [00:00<00:05,  3.16it/s]\n 20%|██        | 4/20 [00:01<00:05,  3.17it/s]\n 25%|██▌       | 5/20 [00:01<00:04,  3.18it/s]\n 30%|███       | 6/20 [00:01<00:04,  3.19it/s]\n 35%|███▌      | 7/20 [00:02<00:04,  3.18it/s]\n 40%|████      | 8/20 [00:02<00:03,  3.19it/s]\n 45%|████▌     | 9/20 [00:02<00:03,  3.19it/s]\n 50%|█████     | 10/20 [00:03<00:03,  3.19it/s]\n 55%|█████▌    | 11/20 [00:03<00:02,  3.19it/s]\n 60%|██████    | 12/20 [00:03<00:02,  3.19it/s]\n 65%|██████▌   | 13/20 [00:04<00:02,  3.19it/s]\n 70%|███████   | 14/20 [00:04<00:01,  3.19it/s]\n 75%|███████▌  | 15/20 [00:04<00:01,  3.19it/s]\n 80%|████████  | 16/20 [00:05<00:01,  3.19it/s]\n 85%|████████▌ | 17/20 [00:05<00:00,  3.18it/s]\n 90%|█████████ | 18/20 [00:05<00:00,  3.19it/s]\n 95%|█████████▌| 19/20 [00:05<00:00,  3.18it/s]\n100%|██████████| 20/20 [00:06<00:00,  3.18it/s]\n100%|██████████| 20/20 [00:06<00:00,  3.18it/s]\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\n[Tiled VAE]: Done in 6.807s, max VRAM alloc 5145.108 MB",
  "metrics": {
    "predict_time": 8.726893,
    "total_time": 8.76424
  },
  "output": "https://replicate.delivery/pbxt/XhtUIywTlO6tLtEjK5fFYkkqx65YXWmt6jEdSZrJ7ZgBkOFJA/output-20240108161700.jpg",
  "started_at": "2024-01-08T16:16:59.802405Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wg4cdq3bd5dpmfglu7qjhe5zlq",
    "cancel": "https://api.replicate.com/v1/predictions/wg4cdq3bd5dpmfglu7qjhe5zlq/cancel"
  },
  "version": "d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195"
}

Generated in

8.7 seconds

Tweak it ShareReport

Prediction

lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195

Model

lucataco/pasd-magnify:d59e83ee

6c3fz73buinuq3xuzkftzha5e4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.6s

Created

over 1 year ago

Input

image
prompt: girl, clean, high-resolution, 8k, best quality, masterpiece
n_prompt: dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
denoise_steps: 20
guidance_scale: 7.5
upsample_scale: 2
conditioning_scale: 1.1

{
  "image": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
  "prompt": "girl, clean, high-resolution, 8k, best quality, masterpiece",
  "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "denoise_steps": 20,
  "guidance_scale": 7.5,
  "upsample_scale": 2,
  "conditioning_scale": 1.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
      prompt: "girl, clean, high-resolution, 8k, best quality, masterpiece",
      n_prompt: "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      denoise_steps: 20,
      guidance_scale: 7.5,
      upsample_scale: 2,
      conditioning_scale: 1.1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/pasd-magnify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    input={
        "image": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
        "prompt": "girl, clean, high-resolution, 8k, best quality, masterpiece",
        "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "denoise_steps": 20,
        "guidance_scale": 7.5,
        "upsample_scale": 2,
        "conditioning_scale": 1.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/pasd-magnify 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": "lucataco/pasd-magnify:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
    "input": {
      "image": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
      "prompt": "girl, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195 \
  -i 'image="https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png"' \
  -i 'prompt="girl, clean, high-resolution, 8k, best quality, masterpiece"' \
  -i 'n_prompt="dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"' \
  -i 'denoise_steps=20' \
  -i 'guidance_scale=7.5' \
  -i 'upsample_scale=2' \
  -i 'conditioning_scale=1.1'

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/lucataco/pasd-magnify@sha256:d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
      "prompt": "girl, clean, high-resolution, 8k, best quality, masterpiece",
      "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "denoise_steps": 20,
      "guidance_scale": 7.5,
      "upsample_scale": 2,
      "conditioning_scale": 1.1
    }
  }' \
  http://localhost:5000/predictions

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

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
  "outut": "https://replicate.delivery/pbxt/6IbiPH5bcCKVBBUTvOMCdj9bh12NDTFMCLZuefkSnoOQJdKSA/output-20240108161817.jpg"
}

{
  "completed_at": "2024-01-08T16:18:25.464930Z",
  "created_at": "2024-01-08T16:18:16.828123Z",
  "data_removed": false,
  "error": null,
  "id": "6c3fz73buinuq3xuzkftzha5e4",
  "input": {
    "image": "https://replicate.delivery/pbxt/KBvBLCchNnP1CMLd7j3VjvjllMeFVzNGS0u3hvEAJz6nGPMX/27d38eeb2dbbe7c9.png",
    "prompt": "girl, clean, high-resolution, 8k, best quality, masterpiece",
    "n_prompt": "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "denoise_steps": 20,
    "guidance_scale": 7.5,
    "upsample_scale": 2,
    "conditioning_scale": 1.1
  },
  "logs": "Using seed: 12706013\nSeed set to 12706013\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:06,  2.95it/s]\n 10%|█         | 2/20 [00:00<00:05,  3.08it/s]\n 15%|█▌        | 3/20 [00:00<00:05,  3.12it/s]\n 20%|██        | 4/20 [00:01<00:05,  3.13it/s]\n 25%|██▌       | 5/20 [00:01<00:04,  3.14it/s]\n 30%|███       | 6/20 [00:01<00:04,  3.14it/s]\n 35%|███▌      | 7/20 [00:02<00:04,  3.14it/s]\n 40%|████      | 8/20 [00:02<00:03,  3.15it/s]\n 45%|████▌     | 9/20 [00:02<00:03,  3.15it/s]\n 50%|█████     | 10/20 [00:03<00:03,  3.15it/s]\n 55%|█████▌    | 11/20 [00:03<00:02,  3.15it/s]\n 60%|██████    | 12/20 [00:03<00:02,  3.15it/s]\n 65%|██████▌   | 13/20 [00:04<00:02,  3.14it/s]\n 70%|███████   | 14/20 [00:04<00:01,  3.14it/s]\n 75%|███████▌  | 15/20 [00:04<00:01,  3.14it/s]\n 80%|████████  | 16/20 [00:05<00:01,  3.14it/s]\n 85%|████████▌ | 17/20 [00:05<00:00,  3.14it/s]\n 90%|█████████ | 18/20 [00:05<00:00,  3.14it/s]\n 95%|█████████▌| 19/20 [00:06<00:00,  3.14it/s]\n100%|██████████| 20/20 [00:06<00:00,  3.14it/s]\n100%|██████████| 20/20 [00:06<00:00,  3.14it/s]\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\n[Tiled VAE]: Done in 6.860s, max VRAM alloc 5164.369 MB",
  "metrics": {
    "predict_time": 8.600168,
    "total_time": 8.636807
  },
  "output": "https://replicate.delivery/pbxt/6IbiPH5bcCKVBBUTvOMCdj9bh12NDTFMCLZuefkSnoOQJdKSA/output-20240108161817.jpg",
  "started_at": "2024-01-08T16:18:16.864762Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6c3fz73buinuq3xuzkftzha5e4",
    "cancel": "https://api.replicate.com/v1/predictions/6c3fz73buinuq3xuzkftzha5e4/cancel"
  },
  "version": "d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195"
}

Generated in

8.6 seconds

Tweak it ShareReport