georgedavila/sdxl-beethoven-spectrograms-lora:193c41ea

Version

You're looking at a specific version of this model. Jump to the model overview.

georgedavila /sdxl-beethoven-spectrograms-lora:193c41ea

Playground API

Input

myprompt

string

Shift + Return to add a new line

Input prompt (SPECTROGRAM is the style trigger word)

Default: "A SPECTROGRAM image"

promptAddendum

string

Shift + Return to add a new line

Extra terms to add to end of prompt

Default: ""

negative_prompt

string

Shift + Return to add a new line

Negative Prompt

Default: "fuzzy, lone pixels"

outWidth

integer

(minimum: 128, maximum: 4096)

width of output

Default: 1024

outHeight

integer

(minimum: 128, maximum: 4096)

height of output

Default: 1024

guidanceScale

number

(minimum: 0, maximum: 50)

Guidance scale (influence of input text on generation)

Default: 7.5

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

seed

integer

Random seed. Leave blank to randomize the seed

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

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

npx create-replicate --model=georgedavila/sdxl-beethoven-spectrograms-lora

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";
import fs from "node:fs";

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

Run georgedavila/sdxl-beethoven-spectrograms-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "georgedavila/sdxl-beethoven-spectrograms-lora:193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5",
  {
    input: {
      myprompt: "A SPECTROGRAM image",
      outWidth: 1024,
      outHeight: 1024,
      lora_scale: 0.6,
      num_outputs: 1,
      guidanceScale: 7.5,
      promptAddendum: "",
      high_noise_frac: 0.8,
      negative_prompt: "fuzzy, lone pixels",
      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 georgedavila/sdxl-beethoven-spectrograms-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "georgedavila/sdxl-beethoven-spectrograms-lora:193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5",
    input={
        "myprompt": "A SPECTROGRAM image",
        "outWidth": 1024,
        "outHeight": 1024,
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidanceScale": 7.5,
        "promptAddendum": "",
        "high_noise_frac": 0.8,
        "negative_prompt": "fuzzy, lone pixels",
        "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 georgedavila/sdxl-beethoven-spectrograms-lora 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": "georgedavila/sdxl-beethoven-spectrograms-lora:193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5",
    "input": {
      "myprompt": "A SPECTROGRAM image",
      "outWidth": 1024,
      "outHeight": 1024,
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidanceScale": 7.5,
      "promptAddendum": "",
      "high_noise_frac": 0.8,
      "negative_prompt": "fuzzy, lone pixels",
      "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/georgedavila/sdxl-beethoven-spectrograms-lora@sha256:193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5 \
  -i 'myprompt="A SPECTROGRAM image"' \
  -i 'outWidth=1024' \
  -i 'outHeight=1024' \
  -i 'lora_scale=0.6' \
  -i 'num_outputs=1' \
  -i 'guidanceScale=7.5' \
  -i 'promptAddendum=""' \
  -i 'high_noise_frac=0.8' \
  -i 'negative_prompt="fuzzy, lone pixels"' \
  -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/georgedavila/sdxl-beethoven-spectrograms-lora@sha256:193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "myprompt": "A SPECTROGRAM image",
      "outWidth": 1024,
      "outHeight": 1024,
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidanceScale": 7.5,
      "promptAddendum": "",
      "high_noise_frac": 0.8,
      "negative_prompt": "fuzzy, lone pixels",
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-29T16:14:09.349554Z",
  "created_at": "2024-05-29T16:12:31.520000Z",
  "data_removed": false,
  "error": null,
  "id": "q38mneyzm1rgm0cfrmfva99c7c",
  "input": {
    "myprompt": "A SPECTROGRAM image",
    "outWidth": 1024,
    "outHeight": 1024,
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidanceScale": 7.5,
    "promptAddendum": "",
    "high_noise_frac": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 9964\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:16,  2.93it/s]\n  4%|▍         | 2/50 [00:00<00:13,  3.60it/s]\n  6%|▌         | 3/50 [00:00<00:12,  3.87it/s]\n  8%|▊         | 4/50 [00:01<00:11,  4.02it/s]\n 10%|█         | 5/50 [00:01<00:10,  4.10it/s]\n 12%|█▏        | 6/50 [00:01<00:10,  4.15it/s]\n 14%|█▍        | 7/50 [00:01<00:10,  4.18it/s]\n 16%|█▌        | 8/50 [00:01<00:09,  4.20it/s]\n 18%|█▊        | 9/50 [00:02<00:09,  4.22it/s]\n 20%|██        | 10/50 [00:02<00:09,  4.22it/s]\n 22%|██▏       | 11/50 [00:02<00:09,  4.23it/s]\n 24%|██▍       | 12/50 [00:02<00:08,  4.23it/s]\n 26%|██▌       | 13/50 [00:03<00:08,  4.24it/s]\n 28%|██▊       | 14/50 [00:03<00:08,  4.24it/s]\n 30%|███       | 15/50 [00:03<00:08,  4.24it/s]\n 32%|███▏      | 16/50 [00:03<00:08,  4.24it/s]\n 34%|███▍      | 17/50 [00:04<00:07,  4.24it/s]\n 36%|███▌      | 18/50 [00:04<00:07,  4.24it/s]\n 38%|███▊      | 19/50 [00:04<00:07,  4.24it/s]\n 40%|████      | 20/50 [00:04<00:07,  4.24it/s]\n 42%|████▏     | 21/50 [00:05<00:06,  4.24it/s]\n 44%|████▍     | 22/50 [00:05<00:06,  4.24it/s]\n 46%|████▌     | 23/50 [00:05<00:06,  4.24it/s]\n 48%|████▊     | 24/50 [00:05<00:06,  4.24it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.24it/s]\n 52%|█████▏    | 26/50 [00:06<00:05,  4.25it/s]\n 54%|█████▍    | 27/50 [00:06<00:05,  4.26it/s]\n 56%|█████▌    | 28/50 [00:06<00:05,  4.26it/s]\n 58%|█████▊    | 29/50 [00:06<00:04,  4.26it/s]\n 60%|██████    | 30/50 [00:07<00:04,  4.27it/s]\n 62%|██████▏   | 31/50 [00:07<00:04,  4.27it/s]\n 64%|██████▍   | 32/50 [00:07<00:04,  4.27it/s]\n 66%|██████▌   | 33/50 [00:07<00:03,  4.27it/s]\n 68%|██████▊   | 34/50 [00:08<00:03,  4.26it/s]\n 70%|███████   | 35/50 [00:08<00:03,  4.26it/s]\n 72%|███████▏  | 36/50 [00:08<00:03,  4.26it/s]\n 74%|███████▍  | 37/50 [00:08<00:03,  4.26it/s]\n 76%|███████▌  | 38/50 [00:09<00:02,  4.26it/s]\n 78%|███████▊  | 39/50 [00:09<00:02,  4.26it/s]\n 80%|████████  | 40/50 [00:09<00:02,  4.26it/s]\n 82%|████████▏ | 41/50 [00:09<00:02,  4.26it/s]\n 84%|████████▍ | 42/50 [00:09<00:01,  4.26it/s]\n 86%|████████▌ | 43/50 [00:10<00:01,  4.26it/s]\n 88%|████████▊ | 44/50 [00:10<00:01,  4.25it/s]\n 90%|█████████ | 45/50 [00:10<00:01,  4.25it/s]\n 92%|█████████▏| 46/50 [00:10<00:00,  4.25it/s]\n 94%|█████████▍| 47/50 [00:11<00:00,  4.25it/s]\n 96%|█████████▌| 48/50 [00:11<00:00,  4.25it/s]\n 98%|█████████▊| 49/50 [00:11<00:00,  4.25it/s]\n100%|██████████| 50/50 [00:11<00:00,  4.26it/s]\n100%|██████████| 50/50 [00:11<00:00,  4.22it/s]",
  "metrics": {
    "predict_time": 14.871608,
    "total_time": 97.829554
  },
  "output": [
    "https://replicate.delivery/pbxt/Y9Owe7ENpI12VKYDUNnwWLJXaem0mNHVhflfrqJbjoF9kBlLB/out-0.png"
  ],
  "started_at": "2024-05-29T16:13:54.477946Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/q38mneyzm1rgm0cfrmfva99c7c",
    "cancel": "https://api.replicate.com/v1/predictions/q38mneyzm1rgm0cfrmfva99c7c/cancel"
  },
  "version": "193c41eaa2f90912bb886b75950af5d433eb9e6007c17507e5da11e527ad38e5"
}

Generated in

14.9 seconds

Tweak it ShareReport View full prediction

Using seed: 9964
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:16,  2.93it/s]
  4%|▍         | 2/50 [00:00<00:13,  3.60it/s]
  6%|▌         | 3/50 [00:00<00:12,  3.87it/s]
  8%|▊         | 4/50 [00:01<00:11,  4.02it/s]
 10%|█         | 5/50 [00:01<00:10,  4.10it/s]
 12%|█▏        | 6/50 [00:01<00:10,  4.15it/s]
 14%|█▍        | 7/50 [00:01<00:10,  4.18it/s]
 16%|█▌        | 8/50 [00:01<00:09,  4.20it/s]
 18%|█▊        | 9/50 [00:02<00:09,  4.22it/s]
 20%|██        | 10/50 [00:02<00:09,  4.22it/s]
 22%|██▏       | 11/50 [00:02<00:09,  4.23it/s]
 24%|██▍       | 12/50 [00:02<00:08,  4.23it/s]
 26%|██▌       | 13/50 [00:03<00:08,  4.24it/s]
 28%|██▊       | 14/50 [00:03<00:08,  4.24it/s]
 30%|███       | 15/50 [00:03<00:08,  4.24it/s]
 32%|███▏      | 16/50 [00:03<00:08,  4.24it/s]
 34%|███▍      | 17/50 [00:04<00:07,  4.24it/s]
 36%|███▌      | 18/50 [00:04<00:07,  4.24it/s]
 38%|███▊      | 19/50 [00:04<00:07,  4.24it/s]
 40%|████      | 20/50 [00:04<00:07,  4.24it/s]
 42%|████▏     | 21/50 [00:05<00:06,  4.24it/s]
 44%|████▍     | 22/50 [00:05<00:06,  4.24it/s]
 46%|████▌     | 23/50 [00:05<00:06,  4.24it/s]
 48%|████▊     | 24/50 [00:05<00:06,  4.24it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.24it/s]
 52%|█████▏    | 26/50 [00:06<00:05,  4.25it/s]
 54%|█████▍    | 27/50 [00:06<00:05,  4.26it/s]
 56%|█████▌    | 28/50 [00:06<00:05,  4.26it/s]
 58%|█████▊    | 29/50 [00:06<00:04,  4.26it/s]
 60%|██████    | 30/50 [00:07<00:04,  4.27it/s]
 62%|██████▏   | 31/50 [00:07<00:04,  4.27it/s]
 64%|██████▍   | 32/50 [00:07<00:04,  4.27it/s]
 66%|██████▌   | 33/50 [00:07<00:03,  4.27it/s]
 68%|██████▊   | 34/50 [00:08<00:03,  4.26it/s]
 70%|███████   | 35/50 [00:08<00:03,  4.26it/s]
 72%|███████▏  | 36/50 [00:08<00:03,  4.26it/s]
 74%|███████▍  | 37/50 [00:08<00:03,  4.26it/s]
 76%|███████▌  | 38/50 [00:09<00:02,  4.26it/s]
 78%|███████▊  | 39/50 [00:09<00:02,  4.26it/s]
 80%|████████  | 40/50 [00:09<00:02,  4.26it/s]
 82%|████████▏ | 41/50 [00:09<00:02,  4.26it/s]
 84%|████████▍ | 42/50 [00:09<00:01,  4.26it/s]
 86%|████████▌ | 43/50 [00:10<00:01,  4.26it/s]
 88%|████████▊ | 44/50 [00:10<00:01,  4.25it/s]
 90%|█████████ | 45/50 [00:10<00:01,  4.25it/s]
 92%|█████████▏| 46/50 [00:10<00:00,  4.25it/s]
 94%|█████████▍| 47/50 [00:11<00:00,  4.25it/s]
 96%|█████████▌| 48/50 [00:11<00:00,  4.25it/s]
 98%|█████████▊| 49/50 [00:11<00:00,  4.25it/s]
100%|██████████| 50/50 [00:11<00:00,  4.26it/s]
100%|██████████| 50/50 [00:11<00:00,  4.22it/s]