fermatresearch/sdxl-lcm-lora-controlnet – Run with an API on Replicate

fermatresearch / sdxl-lcm-lora-controlnet

An extremely fast all-in-one model to use LCM with SDXL, ControlNet and custom LoRA url's!

Cold

Public
14.7K runs
A100 (80GB)
GitHub

Run with an API

Playground API Examples Train README Versions

Input

prompt

string

Shift + Return to add a new line

shot in the style of sksfer, a boy playing with some toysshot in the style of sksfer, a boy playing with some toys

Input prompt

Default: "An astronaut riding a rainbow unicorn, cinematic, dramatic"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

batched_prompt

boolean

When active, your prompt will be split by newlines and images will be generated for each individual line

Default: false

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.

controlnet_image

file

Preview

Input image for controlnet, it will be converted to a canny edge image.

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: "LCM"

num_inference_steps

integer

(minimum: 1, maximum: 20)

Number of denoising steps

Default: 6

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 2

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

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

condition_scale

number

(minimum: 0, maximum: 1)

The bigger this number is, the more ControlNet interferes

Default: 0.5

lora_weights

string

Shift + Return to add a new line

https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tarhttps://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar

Replicate LoRA weights to use. Leave blank to use the default weights.

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](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=fermatresearch/sdxl-lcm-lora-controlnet

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

const output = await replicate.run(
  "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "shot in the style of sksfer, a boy playing with some toys",
      scheduler: "LCM",
      lora_scale: 0.9,
      num_outputs: 1,
      lora_weights: "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar",
      batched_prompt: false,
      guidance_scale: 2,
      apply_watermark: true,
      condition_scale: 0.45,
      negative_prompt: "",
      prompt_strength: 0.8,
      controlnet_image: "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png",
      num_inference_steps: 6
    }
  }
);
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 fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "shot in the style of sksfer, a boy playing with some toys",
        "scheduler": "LCM",
        "lora_scale": 0.9,
        "num_outputs": 1,
        "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar",
        "batched_prompt": False,
        "guidance_scale": 2,
        "apply_watermark": True,
        "condition_scale": 0.45,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png",
        "num_inference_steps": 6
    }
)
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 fermatresearch/sdxl-lcm-lora-controlnet 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": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "shot in the style of sksfer, a boy playing with some toys",
      "scheduler": "LCM",
      "lora_scale": 0.9,
      "num_outputs": 1,
      "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar",
      "batched_prompt": false,
      "guidance_scale": 2,
      "apply_watermark": true,
      "condition_scale": 0.45,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png",
      "num_inference_steps": 6
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-14T15:26:54.484430Z",
  "created_at": "2023-11-14T15:26:50.711437Z",
  "data_removed": false,
  "error": null,
  "id": "szk7rylbfq6aosmfuvkfczlogm",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "shot in the style of sksfer, a boy playing with some toys",
    "scheduler": "LCM",
    "lora_scale": 0.9,
    "num_outputs": 1,
    "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar",
    "batched_prompt": false,
    "guidance_scale": 2,
    "apply_watermark": true,
    "condition_scale": 0.45,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png",
    "num_inference_steps": 6
  },
  "logs": "Using seed: 59453\nskipping loading .. weights already loaded\nPrompt: shot in the style of <s0><s1>, a boy playing with some toys\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n  0%|          | 0/6 [00:00<?, ?it/s]\n 17%|█▋        | 1/6 [00:00<00:01,  4.77it/s]\n 33%|███▎      | 2/6 [00:00<00:00,  4.77it/s]\n 50%|█████     | 3/6 [00:00<00:00,  4.77it/s]\n 67%|██████▋   | 4/6 [00:00<00:00,  4.76it/s]\n 83%|████████▎ | 5/6 [00:01<00:00,  4.76it/s]\n100%|██████████| 6/6 [00:01<00:00,  4.76it/s]\n100%|██████████| 6/6 [00:01<00:00,  4.76it/s]",
  "metrics": {
    "predict_time": 3.715988,
    "total_time": 3.772993
  },
  "output": [
    "https://replicate.delivery/pbxt/URStBauvk2KTHl0Be5UaczWxPPdeX5cDm4fyvQYYQ876dowjA/out-0.png"
  ],
  "started_at": "2023-11-14T15:26:50.768442Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/szk7rylbfq6aosmfuvkfczlogm",
    "cancel": "https://api.replicate.com/v1/predictions/szk7rylbfq6aosmfuvkfczlogm/cancel"
  },
  "version": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099"
}

Generated in

3.7 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.12 to run on Replicate, or 8 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 A100 (80GB) GPU hardware. Predictions typically complete within 89 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.