afiaka87 / sd-aesthetic-guidance

Use stable diffusion and aesthetic CLIP embeddings to guide boring outputs to be more aesthetically pleasing.

Cold

Public
4.3K runs
A100 (80GB)
GitHub

Run with an API

Playground API Examples README Versions

Prediction

afiaka87/sd-aesthetic-guidance:1af76e80

Model

afiaka87/sd-aesthetic-guidance:1af76e80

wnuakmdzg5cldco2vqleeiykku

Status

Succeeded

Source

Web

Hardware

–

Total duration

7.6s

Created

over 2 years ago

Input

width: 512
height: 512
prompt: an image of a scissors
num_outputs: 1
guidance_scale: 7.5
prompt_strength: 0.8
aesthetic_rating: "8"
aesthetic_weight: "0.2"
num_inference_steps: "90"

{
  "width": 512,
  "height": 512,
  "prompt": "an image of a scissors",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "aesthetic_rating": "8",
  "aesthetic_weight": "0.2",
  "num_inference_steps": "90"
}

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 afiaka87/sd-aesthetic-guidance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "afiaka87/sd-aesthetic-guidance:1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "an image of a scissors",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      aesthetic_rating: "8",
      aesthetic_weight: "0.2",
      num_inference_steps: "90"
    }
  }
);
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 afiaka87/sd-aesthetic-guidance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "afiaka87/sd-aesthetic-guidance:1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8",
    input={
        "width": 512,
        "height": 512,
        "prompt": "an image of a scissors",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "aesthetic_rating": "8",
        "aesthetic_weight": "0.2",
        "num_inference_steps": "90"
    }
)
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 afiaka87/sd-aesthetic-guidance 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": "1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "an image of a scissors",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "aesthetic_rating": "8",
      "aesthetic_weight": "0.2",
      "num_inference_steps": "90"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run afiaka87/sd-aesthetic-guidance using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/afiaka87/sd-aesthetic-guidance@sha256:1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8 \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="an image of a scissors"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'prompt_strength=0.8' \
  -i 'aesthetic_rating="8"' \
  -i 'aesthetic_weight="0.2"' \
  -i 'num_inference_steps="90"'

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

Pull and run afiaka87/sd-aesthetic-guidance using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/afiaka87/sd-aesthetic-guidance@sha256:1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "an image of a scissors",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "aesthetic_rating": "8",
      "aesthetic_weight": "0.2",
      "num_inference_steps": "90"
    }
  }' \
  http://localhost:5000/predictions

Output

{
  "completed_at": "2022-09-03T01:38:12.276666Z",
  "created_at": "2022-09-03T01:38:04.684594Z",
  "data_removed": false,
  "error": null,
  "id": "wnuakmdzg5cldco2vqleeiykku",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "an image of a scissors",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "aesthetic_rating": "8",
    "aesthetic_weight": "0.2",
    "num_inference_steps": "90"
  },
  "logs": "Using seed: 36715\n\n0it [00:00, ?it/s]\n2it [00:00, 13.44it/s]\n4it [00:00, 13.10it/s]\n6it [00:00, 13.38it/s]\n8it [00:00, 13.53it/s]\n10it [00:00, 13.55it/s]\n12it [00:00, 13.59it/s]\n14it [00:01, 13.68it/s]\n16it [00:01, 13.51it/s]\n18it [00:01, 13.66it/s]\n20it [00:01, 13.77it/s]\n22it [00:01, 13.84it/s]\n24it [00:01, 13.90it/s]\n26it [00:01, 13.81it/s]\n28it [00:02, 13.76it/s]\n30it [00:02, 13.79it/s]\n32it [00:02, 13.52it/s]\n34it [00:02, 13.67it/s]\n36it [00:02, 13.76it/s]\n38it [00:02, 13.38it/s]\n40it [00:02, 13.53it/s]\n42it [00:03, 13.58it/s]\n44it [00:03, 13.55it/s]\n46it [00:03, 13.60it/s]\n48it [00:03, 13.64it/s]\n50it [00:03, 13.56it/s]\n52it [00:03, 13.61it/s]\n54it [00:03, 13.39it/s]\n56it [00:04, 13.43it/s]\n58it [00:04, 13.54it/s]\n60it [00:04, 13.62it/s]\n62it [00:04, 13.70it/s]\n64it [00:04, 13.76it/s]\n66it [00:04, 13.57it/s]\n68it [00:04, 13.66it/s]\n70it [00:05, 13.67it/s]\n72it [00:05, 13.70it/s]\n74it [00:05, 13.79it/s]\n76it [00:05, 13.79it/s]\n78it [00:05, 13.40it/s]\n80it [00:05, 13.49it/s]\n82it [00:06, 13.55it/s]\n84it [00:06, 13.64it/s]\n86it [00:06, 13.74it/s]\n88it [00:06, 13.64it/s]\n90it [00:06, 13.61it/s]\n90it [00:06, 13.62it/s]",
  "metrics": {
    "predict_time": 7.420751,
    "total_time": 7.592072
  },
  "output": [
    "https://replicate.delivery/mgxm/43afdbae-2343-4c99-8cc3-ba876820c0fa/out-0.png"
  ],
  "started_at": "2022-09-03T01:38:04.855915Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wnuakmdzg5cldco2vqleeiykku",
    "cancel": "https://api.replicate.com/v1/predictions/wnuakmdzg5cldco2vqleeiykku/cancel"
  },
  "version": "1af76e8016e3eaca8d9b053220e3fe3c49f1e770031c6ac6c5ce5fc7a3b115e8"
}

Generated in

7.4 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model