prompthunt/cog-sdxl-controlnet-inference – Run with an API on Replicate

prompthunt / cog-sdxl-controlnet-inference

Cold

Public
312 runs
L40S

Run with an API

Playground API Examples README Versions

Input

lora_weights

string

Shift + Return to add a new line

https://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tarhttps://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tar

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

prompt

string

Shift + Return to add a new line

((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

defined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurrydefined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry

Input Negative Prompt

Default: ""

image

file

Preview

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](https://replicate.com/docs/how-does-replicate-work#safety)

Default: true

pose_image

file

Pose image for controlnet

controlnet_conditioning_scale

number

(minimum: 0, maximum: 4)

How strong the controlnet conditioning is

Default: 0.75

controlnet_start

number

(minimum: 0, maximum: 1)

When controlnet conditioning starts

Default: 0

controlnet_end

number

(minimum: 0, maximum: 1)

When controlnet conditioning ends

Default: 1

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

npx create-replicate --model=prompthunt/cog-sdxl-controlnet-inference

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 prompthunt/cog-sdxl-controlnet-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "prompthunt/cog-sdxl-controlnet-inference:c748f859defb73fe0679ce88bf56c8c203cd9bbe4e81be20325ad65c041a7641",
  {
    input: {
      seed: 1234,
      image: "https://replicate.delivery/pbxt/JtBXIeco0ymI5gPV7hbpb3N8gjPGQePmadfUmXV6njkeM7E9/w1024.jpeg",
      width: 1024,
      height: 1024,
      prompt: "((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      lora_weights: "https://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tar",
      controlnet_end: 1,
      guidance_scale: 3,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "defined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      prompt_strength: 0.8,
      controlnet_start: 0,
      num_inference_steps: 25,
      controlnet_conditioning_scale: 0.5
    }
  }
);

// 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 prompthunt/cog-sdxl-controlnet-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prompthunt/cog-sdxl-controlnet-inference:c748f859defb73fe0679ce88bf56c8c203cd9bbe4e81be20325ad65c041a7641",
    input={
        "seed": 1234,
        "image": "https://replicate.delivery/pbxt/JtBXIeco0ymI5gPV7hbpb3N8gjPGQePmadfUmXV6njkeM7E9/w1024.jpeg",
        "width": 1024,
        "height": 1024,
        "prompt": "((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "lora_weights": "https://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tar",
        "controlnet_end": 1,
        "guidance_scale": 3,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "defined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "prompt_strength": 0.8,
        "controlnet_start": 0,
        "num_inference_steps": 25,
        "controlnet_conditioning_scale": 0.5
    }
)
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 prompthunt/cog-sdxl-controlnet-inference 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": "c748f859defb73fe0679ce88bf56c8c203cd9bbe4e81be20325ad65c041a7641",
    "input": {
      "seed": 1234,
      "image": "https://replicate.delivery/pbxt/JtBXIeco0ymI5gPV7hbpb3N8gjPGQePmadfUmXV6njkeM7E9/w1024.jpeg",
      "width": 1024,
      "height": 1024,
      "prompt": "((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "lora_weights": "https://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tar",
      "controlnet_end": 1,
      "guidance_scale": 3,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "defined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "prompt_strength": 0.8,
      "controlnet_start": 0,
      "num_inference_steps": 25,
      "controlnet_conditioning_scale": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-16T21:28:43.331150Z",
  "created_at": "2023-11-16T21:28:29.220765Z",
  "data_removed": false,
  "error": null,
  "id": "723p4ldb2m6qgp47s5uydlunou",
  "input": {
    "seed": 1234,
    "image": "https://replicate.delivery/pbxt/JtBXIeco0ymI5gPV7hbpb3N8gjPGQePmadfUmXV6njkeM7E9/w1024.jpeg",
    "width": 1024,
    "height": 1024,
    "prompt": "((Moody portrait)) of TOK man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "lora_weights": "https://replicate.delivery/pbxt/yuebGYwbnLUIbiFtTk4tjkkO2BJMcPheYILs7vy7MnzMpB5RA/trained_model.tar",
    "controlnet_end": 1,
    "guidance_scale": 3,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "defined jawline, plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
    "prompt_strength": 0.8,
    "controlnet_start": 0,
    "num_inference_steps": 25,
    "controlnet_conditioning_scale": 0.5
  },
  "logs": "Using seed: 1234\nLoading sdxl txt2img pipeline...\nLoading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  6.99it/s]\nLoading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00,  6.95it/s]\nLoading pipeline components...:  86%|████████▌ | 6/7 [00:01<00:00,  5.11it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  6.08it/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 controlnet model\nimg2img mode\nPrompt: ((Moody portrait)) of <s0><s1> man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:05,  3.69it/s]\n 10%|█         | 2/20 [00:00<00:04,  3.68it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  3.68it/s]\n 20%|██        | 4/20 [00:01<00:04,  3.67it/s]\n 25%|██▌       | 5/20 [00:01<00:04,  3.67it/s]\n 30%|███       | 6/20 [00:01<00:03,  3.67it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  3.68it/s]\n 40%|████      | 8/20 [00:02<00:03,  3.68it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  3.68it/s]\n 50%|█████     | 10/20 [00:02<00:02,  3.68it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  3.68it/s]\n 60%|██████    | 12/20 [00:03<00:02,  3.68it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  3.68it/s]\n 70%|███████   | 14/20 [00:03<00:01,  3.68it/s]\n 75%|███████▌  | 15/20 [00:04<00:01,  3.68it/s]\n 80%|████████  | 16/20 [00:04<00:01,  3.68it/s]\n 85%|████████▌ | 17/20 [00:04<00:00,  3.68it/s]\n 90%|█████████ | 18/20 [00:04<00:00,  3.68it/s]\n 95%|█████████▌| 19/20 [00:05<00:00,  3.68it/s]\n100%|██████████| 20/20 [00:05<00:00,  3.68it/s]\n100%|██████████| 20/20 [00:05<00:00,  3.68it/s]",
  "metrics": {
    "predict_time": 14.054828,
    "total_time": 14.110385
  },
  "output": [
    "https://replicate.delivery/pbxt/bEf9XAvle3vSckOAyTBXmMSOYIqbf0jdgDGbtKTCKVAVcHyjA/out-0.png"
  ],
  "started_at": "2023-11-16T21:28:29.276322Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/723p4ldb2m6qgp47s5uydlunou",
    "cancel": "https://api.replicate.com/v1/predictions/723p4ldb2m6qgp47s5uydlunou/cancel"
  },
  "version": "c748f859defb73fe0679ce88bf56c8c203cd9bbe4e81be20325ad65c041a7641"
}

Generated in

14.1 seconds

Tweak itReport

Using seed: 1234
Loading sdxl txt2img pipeline...
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  29%|██▊       | 2/7 [00:00<00:00,  6.99it/s]
Loading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00,  6.95it/s]
Loading pipeline components...:  86%|████████▌ | 6/7 [00:01<00:00,  5.11it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  6.08it/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 controlnet model
img2img mode
Prompt: ((Moody portrait)) of <s0><s1> man wearing glasses dressed in arctic fashion against an arctic backdrop with iceberg influences, perfect eyes
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:05,  3.69it/s]
 10%|█         | 2/20 [00:00<00:04,  3.68it/s]
 15%|█▌        | 3/20 [00:00<00:04,  3.68it/s]
 20%|██        | 4/20 [00:01<00:04,  3.67it/s]
 25%|██▌       | 5/20 [00:01<00:04,  3.67it/s]
 30%|███       | 6/20 [00:01<00:03,  3.67it/s]
 35%|███▌      | 7/20 [00:01<00:03,  3.68it/s]
 40%|████      | 8/20 [00:02<00:03,  3.68it/s]
 45%|████▌     | 9/20 [00:02<00:02,  3.68it/s]
 50%|█████     | 10/20 [00:02<00:02,  3.68it/s]
 55%|█████▌    | 11/20 [00:02<00:02,  3.68it/s]
 60%|██████    | 12/20 [00:03<00:02,  3.68it/s]
 65%|██████▌   | 13/20 [00:03<00:01,  3.68it/s]
 70%|███████   | 14/20 [00:03<00:01,  3.68it/s]
 75%|███████▌  | 15/20 [00:04<00:01,  3.68it/s]
 80%|████████  | 16/20 [00:04<00:01,  3.68it/s]
 85%|████████▌ | 17/20 [00:04<00:00,  3.68it/s]
 90%|█████████ | 18/20 [00:04<00:00,  3.68it/s]
 95%|█████████▌| 19/20 [00:05<00:00,  3.68it/s]
100%|██████████| 20/20 [00:05<00:00,  3.68it/s]
100%|██████████| 20/20 [00:05<00:00,  3.68it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.016 to run on Replicate, or 62 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 17 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.