zylim0702/sdxl-lora-customize-model – Run with an API on Replicate

zylim0702 / sdxl-lora-customize-model

Introducing a text-to-image AI that crafts stunning 1024x1024 visuals. Load LoRa models via URLs for instant outputs. Train using this link: https://replicate.com/zylim0702/sdxl-lora-customize-training.

Cold

Public
94.9K runs
L40S

Run with an API

Playground API Examples Train README Versions

Input

Lora_url

*string

Shift + Return to add a new line

https://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tarhttps://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tar

Load Lora model

prompt

string

Shift + Return to add a new line

a photo of TOK , white background, pink blazer, american hairstylea photo of TOK , white background, pink blazer, american hairstyle

Input prompt

Default: "An TOK 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

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

npx create-replicate --model=zylim0702/sdxl-lora-customize-model

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 zylim0702/sdxl-lora-customize-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zylim0702/sdxl-lora-customize-model:5a2b1cff79a2cf60d2a498b424795a90e26b7a3992fbd13b340f73ff4942b81e",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "a photo of TOK , white background, pink blazer, american hairstyle",
      refine: "no_refiner",
      Lora_url: "https://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tar",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 4,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 20
    }
  }
);
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 zylim0702/sdxl-lora-customize-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zylim0702/sdxl-lora-customize-model:5a2b1cff79a2cf60d2a498b424795a90e26b7a3992fbd13b340f73ff4942b81e",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "a photo of TOK , white background, pink blazer, american hairstyle",
        "refine": "no_refiner",
        "Lora_url": "https://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tar",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 20
    }
)
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 zylim0702/sdxl-lora-customize-model 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": "5a2b1cff79a2cf60d2a498b424795a90e26b7a3992fbd13b340f73ff4942b81e",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "a photo of TOK , white background, pink blazer, american hairstyle",
      "refine": "no_refiner",
      "Lora_url": "https://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tar",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-08-20T08:13:23.776805Z",
  "created_at": "2023-08-20T08:12:47.927861Z",
  "data_removed": false,
  "error": null,
  "id": "2ygygulbup6s4ynexsp2n5c3ua",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "a photo of TOK , white background, pink blazer, american hairstyle",
    "refine": "no_refiner",
    "Lora_url": "https://replicate.delivery/pbxt/aEt6InPOlTpZJZ9Y1664pLuWBf5ZdIKdjDK4FmHVB2EA47tIA/trained_model.tar",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 4,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "prompt_strength": 0.8,
    "num_inference_steps": 20
  },
  "logs": "Loading sdxl txt2img pipeline...\nLoading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...:  14%|█▍        | 1/7 [00:00<00:02,  2.77it/s]\nLoading pipeline components...:  29%|██▊       | 2/7 [00:01<00:03,  1.48it/s]\nLoading pipeline components...:  43%|████▎     | 3/7 [00:01<00:02,  1.90it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  5.68it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  3.95it/s]\nLoading fine-tuned model\nDoes not have Unet. Assume we are using LoRA\nLoading Unet LoRA\nLoading SDXL img2img pipeline...\nLoading SDXL inpaint pipeline...\nLoading SDXL refiner pipeline...\nLoading refiner pipeline...\nLoading pipeline components...:   0%|          | 0/4 [00:00<?, ?it/s]\nLoading pipeline components...:  25%|██▌       | 1/4 [00:00<00:01,  1.52it/s]\nLoading pipeline components...: 100%|██████████| 4/4 [00:00<00:00,  5.71it/s]\nUsing seed: 8931\nPrompt: a photo of <s0><s1> , white background, pink blazer, american hairstyle\ntxt2img mode\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.00it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.00it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.00it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.00it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.00it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.00it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.00it/s]\n 40%|████      | 8/20 [00:07<00:12,  1.00s/it]\n 45%|████▌     | 9/20 [00:08<00:11,  1.00s/it]\n 50%|█████     | 10/20 [00:09<00:09,  1.00it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.00it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.00it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.00it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.00it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.00it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.00it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.00it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.00it/s]\n 95%|█████████▌| 19/20 [00:18<00:01,  1.00s/it]\n100%|██████████| 20/20 [00:19<00:00,  1.00s/it]\n100%|██████████| 20/20 [00:19<00:00,  1.00it/s]",
  "metrics": {
    "predict_time": 35.840837,
    "total_time": 35.848944
  },
  "output": [
    "https://replicate.delivery/pbxt/Zk65CFgBb5IFJVh3wHmocSMGbgZ1jLIvTeeo8b31B3ph03bRA/out-0.png",
    "https://replicate.delivery/pbxt/cHq7PLwgkWb8LlFYXOepVna3PY5dfhbeJQQcMxXfdfrXke9WE/out-1.png",
    "https://replicate.delivery/pbxt/1qSkUORcadLnEJDxNPtLXdnCMBkEp9jmDxKyGIR9mOuI99WE/out-2.png",
    "https://replicate.delivery/pbxt/nSoKenfp8aqFTkQ4qcDeifAOKbPXeRarzT6fj3I1cm6zI99WE/out-3.png"
  ],
  "started_at": "2023-08-20T08:12:47.935968Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2ygygulbup6s4ynexsp2n5c3ua",
    "cancel": "https://api.replicate.com/v1/predictions/2ygygulbup6s4ynexsp2n5c3ua/cancel"
  },
  "version": "5a2b1cff79a2cf60d2a498b424795a90e26b7a3992fbd13b340f73ff4942b81e"
}

Generated in

35.9 seconds

Tweak itReport

Loading sdxl txt2img pipeline...
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:02,  2.77it/s]
Loading pipeline components...:  29%|██▊       | 2/7 [00:01<00:03,  1.48it/s]
Loading pipeline components...:  43%|████▎     | 3/7 [00:01<00:02,  1.90it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  5.68it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  3.95it/s]
Loading fine-tuned model
Does not have Unet. Assume we are using LoRA
Loading Unet LoRA
Loading SDXL img2img pipeline...
Loading SDXL inpaint pipeline...
Loading SDXL refiner pipeline...
Loading refiner pipeline...
Loading pipeline components...:   0%|          | 0/4 [00:00<?, ?it/s]
Loading pipeline components...:  25%|██▌       | 1/4 [00:00<00:01,  1.52it/s]
Loading pipeline components...: 100%|██████████| 4/4 [00:00<00:00,  5.71it/s]
Using seed: 8931
Prompt: a photo of <s0><s1> , white background, pink blazer, american hairstyle
txt2img mode
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:18,  1.00it/s]
 10%|█         | 2/20 [00:01<00:17,  1.00it/s]
 15%|█▌        | 3/20 [00:02<00:16,  1.00it/s]
 20%|██        | 4/20 [00:03<00:15,  1.00it/s]
 25%|██▌       | 5/20 [00:04<00:14,  1.00it/s]
 30%|███       | 6/20 [00:05<00:13,  1.00it/s]
 35%|███▌      | 7/20 [00:06<00:12,  1.00it/s]
 40%|████      | 8/20 [00:07<00:12,  1.00s/it]
 45%|████▌     | 9/20 [00:08<00:11,  1.00s/it]
 50%|█████     | 10/20 [00:09<00:09,  1.00it/s]
 55%|█████▌    | 11/20 [00:10<00:08,  1.00it/s]
 60%|██████    | 12/20 [00:11<00:07,  1.00it/s]
 65%|██████▌   | 13/20 [00:12<00:06,  1.00it/s]
 70%|███████   | 14/20 [00:13<00:05,  1.00it/s]
 75%|███████▌  | 15/20 [00:14<00:04,  1.00it/s]
 80%|████████  | 16/20 [00:15<00:03,  1.00it/s]
 85%|████████▌ | 17/20 [00:16<00:02,  1.00it/s]
 90%|█████████ | 18/20 [00:17<00:01,  1.00it/s]
 95%|█████████▌| 19/20 [00:18<00:01,  1.00s/it]
100%|██████████| 20/20 [00:19<00:00,  1.00s/it]
100%|██████████| 20/20 [00:19<00:00,  1.00it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.093 to run on Replicate, or 10 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 L40S GPU hardware. Predictions typically complete within 96 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Introducing SDXL LoRa Model: Your Canvas, Your Creativity, Your LoRa

Discover a visionary text-to-image AI, crafting exquisite 1024x1024 visuals. Elevate your artistry further – seamlessly load LoRa models via URLs for unique outputs. To train, explore: Link. Unleash creativity at its finest.

Unlock the extraordinary possibilities of SDXL LoRa Model – where creativity meets customization in perfect harmony. Created by Stability AI, this groundbreaking technology empowers you to effortlessly load and personalize your very own LoRa models, giving wings to your artistic aspirations.

Tailored LoRa Magic: With SDXL LoRa Model, the spotlight is on you. Seamlessly load your customized LoRa models into the system and watch as your unique artistic expressions take center stage.

Your Imagination, Your Rules: Crafted a LoRa model that speaks your language? Now you can seamlessly integrate it into SDXL’s powerful framework. Define the rules, refine the details, and generate awe-inspiring 1024x1024 images that resonate with your distinct style.

Elevate with Ease: Incorporating your customized LoRa model into SDXL is a breeze. Our intuitive interface ensures a seamless process – just upload, personalize, and witness your creativity come alive.

Limitless Versatility: Whether you’re an artist, a designer, or a visionary, SDXL LoRa Model paves the way for endless possibilities. Fuel your ingenuity, transform images, and redefine the boundaries of customization with the fusion of SDXL and your very own LoRa models.

SDXL LoRa Model: Your Vision, Your Model, Your Masterpiece

Experience the fusion of innovation and personalization with SDXL LoRa Model. Embrace the power to load, customize, and create alongside your tailored LoRa models. Your canvas awaits – step into a realm where your imagination knows no bounds.