pnyompen/sd-controlnet-lora – Run with an API on Replicate

pnyompen / sd-controlnet-lora

SD1.5 Canny controlnet with LoRA support.

Cold

Public
548.6K runs
T4
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

An astronaut riding a rainbow unicorn, In the style of oil paintingAn astronaut riding a rainbow unicorn, In the style of oil painting

Input prompt

Default: "An astronaut riding a rainbow unicorn"

image

file

Input image for img2img or inpaint mode

img2img

boolean

Use img2img pipeline, it will use the image input both as the control image and the base image.

Default: false

auto_generate_caption

boolean

Use BLIP to generate captions for the input images

Default: false

generated_caption_weight

number

(minimum: 0)

Weight for the generated caption

Default: 0.5

condition_scale

number

(minimum: 0, maximum: 2)

The bigger this number is, the more ControlNet interferes

Default: 1.1

strength

number

(minimum: 0, maximum: 1)

When img2img is active, the denoising strength. 1 means total destruction of the input image.

Default: 0.8

ip_adapter_scale

number

(minimum: 0)

Scale for the IP Adapter

Default: 1

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 30

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

seed

integer

Random seed. Leave blank to randomize the seed

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.95

lora_weights

string

Shift + Return to add a new line

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

remove_bg

boolean

Remove background from the input image

Default: false

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

npx create-replicate --model=pnyompen/sd-controlnet-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";

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

Run pnyompen/sd-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "pnyompen/sd-controlnet-lora:37ceaf8d4df13e7fe7f1320413189c641c825210df7e40bc21072634a10029bb",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JiOTMCHj4oGrTTf8Pg2r7vyI8YdXc5jL2IDyC2SfhuggjYe6/out-0%20%281%29.png",
      prompt: "An astronaut riding a rainbow unicorn, In the style of oil painting",
      img2img: true,
      strength: 1,
      remove_bg: false,
      scheduler: "KarrasDPM",
      lora_scale: 0.95,
      num_outputs: 1,
      guidance_scale: 7.5,
      condition_scale: 0.5,
      negative_prompt: "worst quality, photorealistic ",
      ip_adapter_scale: 0.1,
      num_inference_steps: 15,
      auto_generate_caption: true,
      generated_caption_weight: 0.1
    }
  }
);

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

output = replicate.run(
    "pnyompen/sd-controlnet-lora:37ceaf8d4df13e7fe7f1320413189c641c825210df7e40bc21072634a10029bb",
    input={
        "image": "https://replicate.delivery/pbxt/JiOTMCHj4oGrTTf8Pg2r7vyI8YdXc5jL2IDyC2SfhuggjYe6/out-0%20%281%29.png",
        "prompt": "An astronaut riding a rainbow unicorn, In the style of oil painting",
        "img2img": True,
        "strength": 1,
        "remove_bg": False,
        "scheduler": "KarrasDPM",
        "lora_scale": 0.95,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "condition_scale": 0.5,
        "negative_prompt": "worst quality, photorealistic ",
        "ip_adapter_scale": 0.1,
        "num_inference_steps": 15,
        "auto_generate_caption": True,
        "generated_caption_weight": 0.1
    }
)
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 pnyompen/sd-controlnet-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": "37ceaf8d4df13e7fe7f1320413189c641c825210df7e40bc21072634a10029bb",
    "input": {
      "image": "https://replicate.delivery/pbxt/JiOTMCHj4oGrTTf8Pg2r7vyI8YdXc5jL2IDyC2SfhuggjYe6/out-0%20%281%29.png",
      "prompt": "An astronaut riding a rainbow unicorn, In the style of oil painting",
      "img2img": true,
      "strength": 1,
      "remove_bg": false,
      "scheduler": "KarrasDPM",
      "lora_scale": 0.95,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "condition_scale": 0.5,
      "negative_prompt": "worst quality, photorealistic ",
      "ip_adapter_scale": 0.1,
      "num_inference_steps": 15,
      "auto_generate_caption": true,
      "generated_caption_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-07-23T22:11:22.266318Z",
  "created_at": "2024-07-23T22:11:17.166000Z",
  "data_removed": false,
  "error": null,
  "id": "nsqe78gr5srge0cgw6k8pbv89g",
  "input": {
    "image": "https://replicate.delivery/pbxt/JiOTMCHj4oGrTTf8Pg2r7vyI8YdXc5jL2IDyC2SfhuggjYe6/out-0%20%281%29.png",
    "prompt": "An astronaut riding a rainbow unicorn, In the style of oil painting",
    "img2img": true,
    "strength": 1,
    "scheduler": "KarrasDPM",
    "lora_scale": 0.95,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "condition_scale": 0.5,
    "negative_prompt": "worst quality, photorealistic ",
    "ip_adapter_scale": 0.1,
    "num_inference_steps": 15,
    "auto_generate_caption": true,
    "generated_caption_weight": 0.1
  },
  "logs": "Using seed: 60585\nOriginal width:1024, height:1024\nAspect Ratio: 1.00\nnew_width:512, new_height:512\nauto_generate_caption mode\nGenerating captions\nGenerated captions ['portrait of a beautiful young woman in a city street']\nGenerating captions took:  0.4332544803619385\nPrompt: (\"An astronaut riding a rainbow unicorn, In the style of oil painting\", \"portrait of a beautiful young woman in a city street\").blend(1, 0.1)\nimg2img mode\n  0%|          | 0/15 [00:00<?, ?it/s]\n  7%|▋         | 1/15 [00:00<00:01,  9.49it/s]\n 13%|█▎        | 2/15 [00:00<00:02,  6.12it/s]\n 20%|██        | 3/15 [00:00<00:02,  5.51it/s]\n 27%|██▋       | 4/15 [00:00<00:02,  5.29it/s]\n 33%|███▎      | 5/15 [00:00<00:01,  5.05it/s]\n 40%|████      | 6/15 [00:01<00:01,  4.93it/s]\n 47%|████▋     | 7/15 [00:01<00:01,  4.90it/s]\n 53%|█████▎    | 8/15 [00:01<00:01,  4.88it/s]\n 60%|██████    | 9/15 [00:01<00:01,  4.86it/s]\n 67%|██████▋   | 10/15 [00:01<00:01,  4.85it/s]\n 73%|███████▎  | 11/15 [00:02<00:00,  4.85it/s]\n 80%|████████  | 12/15 [00:02<00:00,  4.81it/s]\n 87%|████████▋ | 13/15 [00:02<00:00,  4.81it/s]\n 93%|█████████▎| 14/15 [00:02<00:00,  4.80it/s]\n100%|██████████| 15/15 [00:03<00:00,  4.81it/s]\n100%|██████████| 15/15 [00:03<00:00,  4.98it/s]",
  "metrics": {
    "predict_time": 5.077333746,
    "total_time": 5.100318
  },
  "output": [
    "https://replicate.delivery/czjl/mdTFmveZmU1LN6ryofjfQgTsS9YQ4zqh02UInvXlJ9jUk7WmA/out-0.png"
  ],
  "started_at": "2024-07-23T22:11:17.188984Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nsqe78gr5srge0cgw6k8pbv89g",
    "cancel": "https://api.replicate.com/v1/predictions/nsqe78gr5srge0cgw6k8pbv89g/cancel"
  },
  "version": "45f27d985ae0409c990d1c23cbb9656f3ef8ed826078dd606b3af243e09d6244"
}

Generated in

5.1 seconds

Tweak it Share Report

This output was created using a different version of the model, pnyompen/sd-controlnet-lora:45f27d98.

Examples

View more examples

Run time and cost

This model costs approximately $0.013 to run on Replicate, or 76 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 T4 GPU hardware. Predictions typically complete within 60 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.