jagilley/stable-diffusion-upscaler – Run with an API on Replicate

jagilley / stable-diffusion-upscaler

Upscale images with Stable Diffusion

Cold

Public
3.5K runs
T4
GitHub

Run with an API

Playground API Examples README Versions

Input

image

*file

Image to be upscaled

scale

number

(minimum: 0, maximum: 10)

Factor to scale image by

Default: 1.5

prompt

string

Shift + Return to add a new line

Prompt. Not strictly required but can subtly affect the upscaling result.

Default: ""

num_samples

integer

Number of samples to generate

Default: 1

batch_size

integer

Batch size

Default: 1

guidance_scale

number

(minimum: 0, maximum: 10)

Scale factor for guidance

Default: 1

decoder

string

Decoder to use

Default: "finetuned_840k"

noise_aug_level

number

(minimum: 0, maximum: 0.6)

Noise augmentation level

Default: 0

noise_aug_type

string

Noise augmentation type

Default: "gaussian"

sampler

string

Sampler to use

Default: "k_dpm_adaptive"

steps

integer

Number of steps to take in the diffusion process

Default: 10

tol_scale

number

Tolerance scale

Default: 0.25

eta

number

ETA

Default: 1

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

npx create-replicate --model=jagilley/stable-diffusion-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 jagilley/stable-diffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jagilley/stable-diffusion-upscaler:4d0aeee7387b1170b0f6f42bdf14c7d9d8e00a15430d95446ad7426dc61fc3d8",
  {
    input: {
      eta: 1,
      image: "https://replicate.delivery/pbxt/IHlAm5lcJQkjWUh0cHS6L7SZff9ODH0TyFvplbFg8VOcOwmR/out-2.png",
      scale: 4,
      steps: 10,
      prompt: "",
      decoder: "finetuned_840k",
      sampler: "k_dpm_adaptive",
      tol_scale: 0.25,
      batch_size: 1,
      num_samples: 1,
      guidance_scale: 1,
      noise_aug_type: "gaussian",
      noise_aug_level: 0
    }
  }
);
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 jagilley/stable-diffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jagilley/stable-diffusion-upscaler:4d0aeee7387b1170b0f6f42bdf14c7d9d8e00a15430d95446ad7426dc61fc3d8",
    input={
        "eta": 1,
        "image": "https://replicate.delivery/pbxt/IHlAm5lcJQkjWUh0cHS6L7SZff9ODH0TyFvplbFg8VOcOwmR/out-2.png",
        "scale": 4,
        "steps": 10,
        "prompt": "",
        "decoder": "finetuned_840k",
        "sampler": "k_dpm_adaptive",
        "tol_scale": 0.25,
        "batch_size": 1,
        "num_samples": 1,
        "guidance_scale": 1,
        "noise_aug_type": "gaussian",
        "noise_aug_level": 0
    }
)
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 jagilley/stable-diffusion-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": "4d0aeee7387b1170b0f6f42bdf14c7d9d8e00a15430d95446ad7426dc61fc3d8",
    "input": {
      "eta": 1,
      "image": "https://replicate.delivery/pbxt/IHlAm5lcJQkjWUh0cHS6L7SZff9ODH0TyFvplbFg8VOcOwmR/out-2.png",
      "scale": 4,
      "steps": 10,
      "prompt": "",
      "decoder": "finetuned_840k",
      "sampler": "k_dpm_adaptive",
      "tol_scale": 0.25,
      "batch_size": 1,
      "num_samples": 1,
      "guidance_scale": 1,
      "noise_aug_type": "gaussian",
      "noise_aug_level": 0
    }
  }' \
  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/jagilley/stable-diffusion-upscaler@sha256:4d0aeee7387b1170b0f6f42bdf14c7d9d8e00a15430d95446ad7426dc61fc3d8 \
  -i 'eta=1' \
  -i 'image="https://replicate.delivery/pbxt/IHlAm5lcJQkjWUh0cHS6L7SZff9ODH0TyFvplbFg8VOcOwmR/out-2.png"' \
  -i 'scale=4' \
  -i 'steps=10' \
  -i 'prompt=""' \
  -i 'decoder="finetuned_840k"' \
  -i 'sampler="k_dpm_adaptive"' \
  -i 'tol_scale=0.25' \
  -i 'batch_size=1' \
  -i 'num_samples=1' \
  -i 'guidance_scale=1' \
  -i 'noise_aug_type="gaussian"' \
  -i 'noise_aug_level=0'

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/jagilley/stable-diffusion-upscaler@sha256:4d0aeee7387b1170b0f6f42bdf14c7d9d8e00a15430d95446ad7426dc61fc3d8
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "eta": 1,
      "image": "https://replicate.delivery/pbxt/IHlAm5lcJQkjWUh0cHS6L7SZff9ODH0TyFvplbFg8VOcOwmR/out-2.png",
      "scale": 4,
      "steps": 10,
      "prompt": "",
      "decoder": "finetuned_840k",
      "sampler": "k_dpm_adaptive",
      "tol_scale": 0.25,
      "batch_size": 1,
      "num_samples": 1,
      "guidance_scale": 1,
      "noise_aug_type": "gaussian",
      "noise_aug_level": 0
    }
  }' \
  http://localhost:5000/predictions

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

Output

Generated in

18.1 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.077 to run on Replicate, or 12 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 T4 GPU hardware. Predictions typically complete within 6 minutes. The predict time for this model varies significantly based on the inputs.

Readme

Upscale images with Stable Diffusion, optionally including a prompt to subtly alter the input image.

Model description

A latent diffusion upscaler for the Stable Diffusion autoencoder.

Developed by: Robin Rombach, Patrick Esser
Model type: Diffusion-based text-to-image generation model
Language(s): English
License: CreativeML Open RAIL++-M License
Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses a fixed, pretrained text encoder (OpenCLIP-ViT/H).
Resources for more information: GitHub Repository.
Cite as:

      @InProceedings{Rombach_2022_CVPR,
          author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
          title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
          booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
          month     = {June},
          year      = {2022},
          pages     = {10684-10695}
      }