codingdudecom/sdxl-mandala – Run with an API on Replicate

codingdudecom / sdxl-mandala

SDXL model for mandalas coloring pages and coloring book designs

Warm

Public
461 runs
L40S
SDXL fine-tune
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a flower TOK mandal design, coloring pages for kids, illustration, white backgrounda flower TOK mandal design, coloring pages for kids, illustration, white background

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

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

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Default: false

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

npx create-replicate --model=codingdudecom/sdxl-mandala

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 codingdudecom/sdxl-mandala using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "codingdudecom/sdxl-mandala:a93e82a77fce729a086caf532323ee798f89c433871ad2921e6fa0c3978e9bda",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "a flower TOK mandal design, coloring pages for kids, illustration, white background",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 30
    }
  }
);

// 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 codingdudecom/sdxl-mandala using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "codingdudecom/sdxl-mandala:a93e82a77fce729a086caf532323ee798f89c433871ad2921e6fa0c3978e9bda",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "a flower TOK mandal design, coloring pages for kids, illustration, white background",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 30
    }
)
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 codingdudecom/sdxl-mandala 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": "a93e82a77fce729a086caf532323ee798f89c433871ad2921e6fa0c3978e9bda",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "a flower TOK mandal design, coloring pages for kids, illustration, white background",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-19T15:08:38.876058Z",
  "created_at": "2024-03-19T15:08:24.066398Z",
  "data_removed": false,
  "error": null,
  "id": "erarfgdbxbsjufsvtjjwh42m7y",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "a flower TOK mandal design, coloring pages for kids, illustration, white background",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": false,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 36811\nEnsuring enough disk space...\nFree disk space: 3363049660416\nDownloading weights: https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar\n2024-03-19T15:08:27Z | INFO  | [ Initiating ] dest=/src/weights-cache/3708132d63d38faa minimum_chunk_size=150M url=https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar\n2024-03-19T15:08:28Z | INFO  | [ Complete ] dest=/src/weights-cache/3708132d63d38faa size=\"186 MB\" total_elapsed=0.443s url=https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar\nb''\nDownloaded weights in 0.5244059562683105 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a flower <s0><s1> mandal design, coloring pages for kids, illustration, white background\ntxt2img mode\n  0%|          | 0/30 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  3%|▎         | 1/30 [00:00<00:11,  2.48it/s]\n  7%|▋         | 2/30 [00:00<00:08,  3.14it/s]\n 10%|█         | 3/30 [00:00<00:07,  3.42it/s]\n 13%|█▎        | 4/30 [00:01<00:07,  3.57it/s]\n 17%|█▋        | 5/30 [00:01<00:06,  3.66it/s]\n 20%|██        | 6/30 [00:01<00:06,  3.71it/s]\n 23%|██▎       | 7/30 [00:01<00:06,  3.75it/s]\n 27%|██▋       | 8/30 [00:02<00:05,  3.78it/s]\n 30%|███       | 9/30 [00:02<00:05,  3.79it/s]\n 33%|███▎      | 10/30 [00:02<00:05,  3.80it/s]\n 37%|███▋      | 11/30 [00:03<00:04,  3.81it/s]\n 40%|████      | 12/30 [00:03<00:04,  3.81it/s]\n 43%|████▎     | 13/30 [00:03<00:04,  3.82it/s]\n 47%|████▋     | 14/30 [00:03<00:04,  3.82it/s]\n 50%|█████     | 15/30 [00:04<00:03,  3.82it/s]\n 53%|█████▎    | 16/30 [00:04<00:03,  3.82it/s]\n 57%|█████▋    | 17/30 [00:04<00:03,  3.81it/s]\n 60%|██████    | 18/30 [00:04<00:03,  3.82it/s]\n 63%|██████▎   | 19/30 [00:05<00:02,  3.81it/s]\n 67%|██████▋   | 20/30 [00:05<00:02,  3.81it/s]\n 70%|███████   | 21/30 [00:05<00:02,  3.81it/s]\n 73%|███████▎  | 22/30 [00:05<00:02,  3.81it/s]\n 77%|███████▋  | 23/30 [00:06<00:01,  3.81it/s]\n 80%|████████  | 24/30 [00:06<00:01,  3.81it/s]\n 83%|████████▎ | 25/30 [00:06<00:01,  3.81it/s]\n 87%|████████▋ | 26/30 [00:06<00:01,  3.80it/s]\n 90%|█████████ | 27/30 [00:07<00:00,  3.81it/s]\n 93%|█████████▎| 28/30 [00:07<00:00,  3.80it/s]\n 97%|█████████▋| 29/30 [00:07<00:00,  3.80it/s]\n100%|██████████| 30/30 [00:08<00:00,  3.80it/s]\n100%|██████████| 30/30 [00:08<00:00,  3.75it/s]",
  "metrics": {
    "predict_time": 10.959069,
    "total_time": 14.80966
  },
  "output": [
    "https://replicate.delivery/pbxt/9Rl9laSO9LJEFRTd4fpvrCTCndUOhFOnPEv46FI9PgP746QJA/out-0.png"
  ],
  "started_at": "2024-03-19T15:08:27.916989Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/erarfgdbxbsjufsvtjjwh42m7y",
    "cancel": "https://api.replicate.com/v1/predictions/erarfgdbxbsjufsvtjjwh42m7y/cancel"
  },
  "version": "914b95a0a2b4ba91dcbff37d28d2c12081bd183c37c50bff865eff96b9252e8b"
}

Generated in

11.0 seconds

Tweak itReport

Using seed: 36811
Ensuring enough disk space...
Free disk space: 3363049660416
Downloading weights: https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar
2024-03-19T15:08:27Z | INFO  | [ Initiating ] dest=/src/weights-cache/3708132d63d38faa minimum_chunk_size=150M url=https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar
2024-03-19T15:08:28Z | INFO  | [ Complete ] dest=/src/weights-cache/3708132d63d38faa size="186 MB" total_elapsed=0.443s url=https://replicate.delivery/pbxt/hRVGxmMRULIfCaVfeyCOaIy3zDcK0iyiW8uN0k06gafukWHKB/trained_model.tar
b''
Downloaded weights in 0.5244059562683105 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a flower <s0><s1> mandal design, coloring pages for kids, illustration, white background
txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)
return F.conv2d(input, weight, bias, self.stride,
  3%|▎         | 1/30 [00:00<00:11,  2.48it/s]
  7%|▋         | 2/30 [00:00<00:08,  3.14it/s]
 10%|█         | 3/30 [00:00<00:07,  3.42it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.57it/s]
 17%|█▋        | 5/30 [00:01<00:06,  3.66it/s]
 20%|██        | 6/30 [00:01<00:06,  3.71it/s]
 23%|██▎       | 7/30 [00:01<00:06,  3.75it/s]
 27%|██▋       | 8/30 [00:02<00:05,  3.78it/s]
 30%|███       | 9/30 [00:02<00:05,  3.79it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.80it/s]
 37%|███▋      | 11/30 [00:03<00:04,  3.81it/s]
 40%|████      | 12/30 [00:03<00:04,  3.81it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.82it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.82it/s]
 50%|█████     | 15/30 [00:04<00:03,  3.82it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.82it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.81it/s]
 60%|██████    | 18/30 [00:04<00:03,  3.82it/s]
 63%|██████▎   | 19/30 [00:05<00:02,  3.81it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.81it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.81it/s]
 73%|███████▎  | 22/30 [00:05<00:02,  3.81it/s]
 77%|███████▋  | 23/30 [00:06<00:01,  3.81it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.81it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.81it/s]
 87%|████████▋ | 26/30 [00:06<00:01,  3.80it/s]
 90%|█████████ | 27/30 [00:07<00:00,  3.81it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.80it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  3.80it/s]
100%|██████████| 30/30 [00:08<00:00,  3.80it/s]
100%|██████████| 30/30 [00:08<00:00,  3.75it/s]

This output was created using a different version of the model, codingdudecom/sdxl-mandala:914b95a0.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

A fine-tuned SDXL model for producing round mandalas coloring pages and coloring book designs.

This is a meticulously fine-tuned SDXL model designed exclusively for generating captivating round mandalas coloring pages and intricate designs for coloring books. Harnessing the power of cutting-edge deep learning techniques, this seamlessly blends creativity with precision, crafting mesmerizing mandalas that inspire tranquility and creativity in every stroke.

With sdxl-mandala, users can effortlessly create an array of mandalas tailored to their preferences, whether seeking intricate symmetrical patterns or soothing geometric arrangements. The model’s advanced algorithms ensure each mandala exudes harmony and balance, inviting individuals to immerse themselves in the therapeutic art of coloring.

Whether you’re an artist seeking inspiration, an educator planning mindfulness activities, or simply someone looking to unwind, sdxl-mandala offers a seamless solution for crafting beautiful mandalas that captivate the imagination and soothe the soul. Unlock a world of creativity with sdxl-mandala – where artistry meets technology in perfect harmony.

Author: @codingdudecom

License: https://raw.githubusercontent.com/Stability-AI/generative-models/main/model_licenses/LICENSE-SDXL1.0

This model and many other models are part of the list of AI text-to-image engine of MockoFun

Example prompts:

“a photo of TOK and mandal pattern in black and white”

“a photo of TOK mandal mandal flower, coloring pages”