philz1337x/clarity-upscaler – Run with an API on Replicate

philz1337x / clarity-upscaler

High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x

Warm

Public
11M runs
A100 (40GB)
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

image

*file

Preview

input image

prompt

string

Shift + Return to add a new line

masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>

Prompt

Default: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>"

negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality, normal quality:2) JuggernautNegative-neg(worst quality, low quality, normal quality:2) JuggernautNegative-neg

Negative Prompt

Default: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg"

scale_factor

number

Scale factor

Default: 2

dynamic

number

(minimum: 1, maximum: 50)

HDR, try from 3 - 9

Default: 6

creativity

number

(minimum: 0, maximum: 1)

Creativity, try from 0.3 - 0.9

Default: 0.35

resemblance

number

(minimum: 0, maximum: 3)

Resemblance, try from 0.3 - 1.6

Default: 0.6

tiling_width

integer

Fractality, set lower tile width for a high Fractality

Default: 112

tiling_height

integer

Fractality, set lower tile height for a high Fractality

Default: 144

sd_model

string

Stable Diffusion model checkpoint

Default: "juggernaut_reborn.safetensors [338b85bc4f]"

scheduler

string

scheduler

Default: "DPM++ 3M SDE Karras"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 18

seed

integer

Random seed. Leave blank to randomize the seed

Default: 1337

downscaling

boolean

Downscale the image before upscaling. Can improve quality and speed for images with high resolution but lower quality

Default: false

downscaling_resolution

integer

Downscaling resolution

Default: 768

lora_links

string

Shift + Return to add a new line

Link to a lora file you want to use in your upscaling. Multiple links possible, seperated by comma

Default: ""

custom_sd_model

string

Shift + Return to add a new line

Default: ""

sharpen

number

(minimum: 0, maximum: 10)

Sharpen the image after upscaling. The higher the value, the more sharpening is applied. 0 for no sharpening

Default: 0

mask

file

Mask image to mark areas that should be preserved during upscaling

handfix

string

Use clarity to fix hands in the image

Default: "disabled"

pattern

boolean

Upscale a pattern with seamless tiling

Default: false

output_format

string

Format of the output images

Default: "png"

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

npx create-replicate --model=philz1337x/clarity-upscaler

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run philz1337x/clarity-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "philz1337x/clarity-upscaler:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
  {
    input: {
      seed: 1337,
      image: "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
      prompt: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
      dynamic: 6,
      handfix: "disabled",
      pattern: false,
      sharpen: 0,
      sd_model: "juggernaut_reborn.safetensors [338b85bc4f]",
      scheduler: "DPM++ 3M SDE Karras",
      creativity: 0.35,
      lora_links: "",
      downscaling: false,
      resemblance: 0.6,
      scale_factor: 2,
      tiling_width: 112,
      output_format: "png",
      tiling_height: 144,
      custom_sd_model: "",
      negative_prompt: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
      num_inference_steps: 18,
      downscaling_resolution: 768
    }
  }
);
console.log(output);

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

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run philz1337x/clarity-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "philz1337x/clarity-upscaler:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
    input={
        "seed": 1337,
        "image": "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
        "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
        "dynamic": 6,
        "handfix": "disabled",
        "pattern": False,
        "sharpen": 0,
        "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
        "scheduler": "DPM++ 3M SDE Karras",
        "creativity": 0.35,
        "lora_links": "",
        "downscaling": False,
        "resemblance": 0.6,
        "scale_factor": 2,
        "tiling_width": 112,
        "output_format": "png",
        "tiling_height": 144,
        "custom_sd_model": "",
        "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
        "num_inference_steps": 18,
        "downscaling_resolution": 768
    }
)
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 philz1337x/clarity-upscaler 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": "dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
    "input": {
      "seed": 1337,
      "image": "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
      "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
      "dynamic": 6,
      "handfix": "disabled",
      "pattern": false,
      "sharpen": 0,
      "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
      "scheduler": "DPM++ 3M SDE Karras",
      "creativity": 0.35,
      "lora_links": "",
      "downscaling": false,
      "resemblance": 0.6,
      "scale_factor": 2,
      "tiling_width": 112,
      "output_format": "png",
      "tiling_height": 144,
      "custom_sd_model": "",
      "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
      "num_inference_steps": 18,
      "downscaling_resolution": 768
    }
  }' \
  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/philz1337x/clarity-upscaler@sha256:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e \
  -i 'seed=1337' \
  -i 'image="https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png"' \
  -i 'prompt="masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>"' \
  -i 'dynamic=6' \
  -i 'handfix="disabled"' \
  -i 'pattern=false' \
  -i 'sharpen=0' \
  -i 'sd_model="juggernaut_reborn.safetensors [338b85bc4f]"' \
  -i 'scheduler="DPM++ 3M SDE Karras"' \
  -i 'creativity=0.35' \
  -i 'lora_links=""' \
  -i 'downscaling=false' \
  -i 'resemblance=0.6' \
  -i 'scale_factor=2' \
  -i 'tiling_width=112' \
  -i 'output_format="png"' \
  -i 'tiling_height=144' \
  -i 'custom_sd_model=""' \
  -i 'negative_prompt="(worst quality, low quality, normal quality:2) JuggernautNegative-neg"' \
  -i 'num_inference_steps=18' \
  -i 'downscaling_resolution=768'

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/philz1337x/clarity-upscaler@sha256:dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 1337,
      "image": "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
      "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
      "dynamic": 6,
      "handfix": "disabled",
      "pattern": false,
      "sharpen": 0,
      "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
      "scheduler": "DPM++ 3M SDE Karras",
      "creativity": 0.35,
      "lora_links": "",
      "downscaling": false,
      "resemblance": 0.6,
      "scale_factor": 2,
      "tiling_width": 112,
      "output_format": "png",
      "tiling_height": 144,
      "custom_sd_model": "",
      "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
      "num_inference_steps": 18,
      "downscaling_resolution": 768
    }
  }' \
  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/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
  "outut": "https://replicate.delivery/pbxt/00paK5p2fY36XykEcte0skfqnSl3akRGTm4TC2l2wiU0E4QlA/1337-89fd2a6e-f5bd-11ee-87b9-bec9d6ff70a9.png"
}

{
  "completed_at": "2024-04-08T15:34:51.385820Z",
  "created_at": "2024-04-08T15:34:38.558000Z",
  "data_removed": false,
  "error": null,
  "id": "snbeynewvsrgp0ceqsc8gjk6sm",
  "input": {
    "seed": 1337,
    "image": "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
    "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
    "dynamic": 6,
    "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
    "scheduler": "DPM++ 3M SDE Karras",
    "creativity": 0.35,
    "lora_links": "",
    "downscaling": false,
    "resemblance": 0.6,
    "scale_factor": 2,
    "tiling_width": 112,
    "tiling_height": 144,
    "custom_sd_model": "",
    "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
    "num_inference_steps": 18,
    "downscaling_resolution": 768
  },
  "logs": "Running prediction\n[Tiled Diffusion] upscaling image with 4x-UltraSharp...\n[Tiled Diffusion] ControlNet found, support is enabled.\n2024-04-08 15:34:42,215 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2024-04-08 15:34:42,215 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model from cache: control_v11f1e_sd15_tile\n2024-04-08 15:34:42,234 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2024-04-08 15:34:42,234 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 1536\n2024-04-08 15:34:42,310 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 0.0993812084197998\nMultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 144x112, Tile count: 4, Batch size: 4, Tile batches: 1 (ext: ContrlNet)\n[Tiled VAE]: the input size is tiny and unnecessary to tile.\nMultiDiffusion Sampling:   0%|          | 0/10 [00:00<?, ?it/s]\n  0%|          | 0/7 [00:00<?, ?it/s]\u001b[A\nTotal progress:   0%|          | 0/7 [00:00<?, ?it/s]\u001b[A\n 14%|█▍        | 1/7 [00:00<00:05,  1.10it/s]\u001b[A\nTotal progress:  29%|██▊       | 2/7 [00:00<00:02,  2.22it/s]\u001b[A\n 29%|██▊       | 2/7 [00:01<00:04,  1.11it/s]\u001b[A\nTotal progress:  43%|████▎     | 3/7 [00:01<00:02,  1.57it/s]\u001b[A\n 43%|████▎     | 3/7 [00:02<00:03,  1.11it/s]\u001b[A\nTotal progress:  57%|█████▋    | 4/7 [00:02<00:02,  1.36it/s]\u001b[A\n 57%|█████▋    | 4/7 [00:03<00:02,  1.11it/s]\u001b[A\nTotal progress:  71%|███████▏  | 5/7 [00:03<00:01,  1.26it/s]\u001b[A\n 71%|███████▏  | 5/7 [00:04<00:01,  1.11it/s]\u001b[A\nTotal progress:  86%|████████▌ | 6/7 [00:04<00:00,  1.21it/s]\u001b[A\n 86%|████████▌ | 6/7 [00:05<00:00,  1.11it/s]\u001b[A\n100%|██████████| 7/7 [00:06<00:00,  1.11it/s]\u001b[A\n100%|██████████| 7/7 [00:06<00:00,  1.11it/s]\nTotal progress: 100%|██████████| 7/7 [00:05<00:00,  1.18it/s]\u001b[A[Tiled VAE]: the input size is tiny and unnecessary to tile.\nTotal progress: 100%|██████████| 7/7 [00:06<00:00,  1.18it/s]\u001b[A\nTotal progress: 100%|██████████| 7/7 [00:06<00:00,  1.11it/s]\nPrediction took 11.742665767669678 seconds",
  "metrics": {
    "predict_time": 12.806754,
    "total_time": 12.82782
  },
  "output": [
    "https://replicate.delivery/pbxt/00paK5p2fY36XykEcte0skfqnSl3akRGTm4TC2l2wiU0E4QlA/1337-89fd2a6e-f5bd-11ee-87b9-bec9d6ff70a9.png"
  ],
  "started_at": "2024-04-08T15:34:38.579066Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/snbeynewvsrgp0ceqsc8gjk6sm",
    "cancel": "https://api.replicate.com/v1/predictions/snbeynewvsrgp0ceqsc8gjk6sm/cancel"
  },
  "version": "3bb9d3412f14261c2f8cfa15a56dd7b33f44af54777c517b860a3f678a5d7f3b"
}

Generated in

12.8 seconds

Tweak it ShareReport

Running prediction
[Tiled Diffusion] upscaling image with 4x-UltraSharp...
[Tiled Diffusion] ControlNet found, support is enabled.
2024-04-08 15:34:42,215 - ControlNet - INFO - unit_separate = False, style_align = False
2024-04-08 15:34:42,215 - ControlNet - INFO - Loading model from cache: control_v11f1e_sd15_tile
2024-04-08 15:34:42,234 - ControlNet - INFO - Using preprocessor: tile_resample
2024-04-08 15:34:42,234 - ControlNet - INFO - preprocessor resolution = 1536
2024-04-08 15:34:42,310 - ControlNet - INFO - ControlNet Hooked - Time = 0.0993812084197998
MultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 144x112, Tile count: 4, Batch size: 4, Tile batches: 1 (ext: ContrlNet)
[Tiled VAE]: the input size is tiny and unnecessary to tile.
MultiDiffusion Sampling:   0%|          | 0/10 [00:00<?, ?it/s]
  0%|          | 0/7 [00:00<?, ?it/s]
Total progress:   0%|          | 0/7 [00:00<?, ?it/s]
 14%|█▍        | 1/7 [00:00<00:05,  1.10it/s]
Total progress:  29%|██▊       | 2/7 [00:00<00:02,  2.22it/s]
 29%|██▊       | 2/7 [00:01<00:04,  1.11it/s]
Total progress:  43%|████▎     | 3/7 [00:01<00:02,  1.57it/s]
 43%|████▎     | 3/7 [00:02<00:03,  1.11it/s]
Total progress:  57%|█████▋    | 4/7 [00:02<00:02,  1.36it/s]
 57%|█████▋    | 4/7 [00:03<00:02,  1.11it/s]
Total progress:  71%|███████▏  | 5/7 [00:03<00:01,  1.26it/s]
 71%|███████▏  | 5/7 [00:04<00:01,  1.11it/s]
Total progress:  86%|████████▌ | 6/7 [00:04<00:00,  1.21it/s]
 86%|████████▌ | 6/7 [00:05<00:00,  1.11it/s]
100%|██████████| 7/7 [00:06<00:00,  1.11it/s]
100%|██████████| 7/7 [00:06<00:00,  1.11it/s]
Total progress: 100%|██████████| 7/7 [00:05<00:00,  1.18it/s][Tiled VAE]: the input size is tiny and unnecessary to tile.
Total progress: 100%|██████████| 7/7 [00:06<00:00,  1.18it/s]
Total progress: 100%|██████████| 7/7 [00:06<00:00,  1.11it/s]
Prediction took 11.742665767669678 seconds

This example was created by a different version, philz1337x/clarity-upscaler:3bb9d341.

Examples

View more examples

Run time and cost

This model costs approximately $0.014 to run on Replicate, or 71 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (40GB) GPU hardware. Predictions typically complete within 12 seconds.

Readme

High resolution image Upscaler and Enhancer.

Updates: https://twitter.com/philz1337x

App: https://ClarityAI.co

Clarity Upscaler TM Clarity AI TM