fermatresearch/high-resolution-controlnet-tile – Run with an API on Replicate

fermatresearch / high-resolution-controlnet-tile

UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.

Cold

Public
615.4K runs
L40S

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a nordic livingroom, 4k interior photography, uhda nordic livingroom, 4k interior photography, uhd

Prompt for the model

image

file

Control image for scribble controlnet

resolution

integer

Image resolution

Default: 2560

resemblance

number

(minimum: 0, maximum: 1)

Conditioning scale for controlnet

Default: 0.85

creativity

number

(minimum: 0.1, maximum: 1)

Denoising strength. 1 means total destruction of the original image

Default: 0.35

hdr

number

(minimum: 0, maximum: 1)

HDR improvement over the original image

Default: 0

scheduler

string

Choose a scheduler.

Default: "DDIM"

steps

integer

Steps

Default: 8

guidance_scale

number

(minimum: 0, maximum: 30)

Scale for classifier-free guidance, should be 0.

Default: 0

seed

integer

Seed

negative_prompt

string

Shift + Return to add a new line

Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutantTeeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant

Negative prompt

Default: "teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"

guess_mode

boolean

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts.

Default: false

lora_sharpness_strength

number

(minimum: -5, maximum: 10)

Strength of the image's sharpness. We don't recommend values above 2.

Default: 1.25

lora_details_strength

number

(minimum: -5, maximum: 3)

Strength of the image's details

Default: 1

format

string

Format of the output.

Default: "jpg"

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

npx create-replicate --model=fermatresearch/high-resolution-controlnet-tile

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/high-resolution-controlnet-tile using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/high-resolution-controlnet-tile:8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975",
  {
    input: {
      hdr: 0,
      image: "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
      steps: 8,
      format: "jpg",
      prompt: "a nordic livingroom, 4k interior photography, uhd",
      scheduler: "DDIM",
      creativity: 0.4,
      guess_mode: false,
      resolution: 2560,
      resemblance: 0.85,
      guidance_scale: 0,
      negative_prompt: "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant",
      lora_details_strength: -0.25,
      lora_sharpness_strength: 0.75
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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/high-resolution-controlnet-tile using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/high-resolution-controlnet-tile:8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975",
    input={
        "hdr": 0,
        "image": "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
        "steps": 8,
        "format": "jpg",
        "prompt": "a nordic livingroom, 4k interior photography, uhd",
        "scheduler": "DDIM",
        "creativity": 0.4,
        "guess_mode": False,
        "resolution": 2560,
        "resemblance": 0.85,
        "guidance_scale": 0,
        "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant",
        "lora_details_strength": -0.25,
        "lora_sharpness_strength": 0.75
    }
)
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/high-resolution-controlnet-tile 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": "8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975",
    "input": {
      "hdr": 0,
      "image": "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
      "steps": 8,
      "format": "jpg",
      "prompt": "a nordic livingroom, 4k interior photography, uhd",
      "scheduler": "DDIM",
      "creativity": 0.4,
      "guess_mode": false,
      "resolution": 2560,
      "resemblance": 0.85,
      "guidance_scale": 0,
      "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant",
      "lora_details_strength": -0.25,
      "lora_sharpness_strength": 0.75
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/fermatresearch/high-resolution-controlnet-tile@sha256:8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975 \
  -i 'hdr=0' \
  -i 'image="https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp"' \
  -i 'steps=8' \
  -i 'format="jpg"' \
  -i 'prompt="a nordic livingroom, 4k interior photography, uhd"' \
  -i 'scheduler="DDIM"' \
  -i 'creativity=0.4' \
  -i 'guess_mode=false' \
  -i 'resolution=2560' \
  -i 'resemblance=0.85' \
  -i 'guidance_scale=0' \
  -i 'negative_prompt="Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"' \
  -i 'lora_details_strength=-0.25' \
  -i 'lora_sharpness_strength=0.75'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/fermatresearch/high-resolution-controlnet-tile@sha256:8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "hdr": 0,
      "image": "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
      "steps": 8,
      "format": "jpg",
      "prompt": "a nordic livingroom, 4k interior photography, uhd",
      "scheduler": "DDIM",
      "creativity": 0.4,
      "guess_mode": false,
      "resolution": 2560,
      "resemblance": 0.85,
      "guidance_scale": 0,
      "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant",
      "lora_details_strength": -0.25,
      "lora_sharpness_strength": 0.75
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
  "outut": "https://replicate.delivery/pbxt/YFlNVWt9oEpTMVEKg69wXDRGtjHSHKV02ESZeChKj69ffiYmA/output.jpg"
}

{
  "completed_at": "2024-07-26T09:01:53.303407Z",
  "created_at": "2024-07-26T08:59:39.746000Z",
  "data_removed": false,
  "error": null,
  "id": "4xg26j3bc9rgm0cgxs28xehaag",
  "input": {
    "hdr": 0,
    "image": "https://replicate.delivery/pbxt/LKnw8rSgafZf4IlAVyPhzpX1TpTVcyfRa1saoaoiSfUYZLiL/fermat_app_a_living_room_modern_and_minimalistic_39b5a58a-e05b-4281-ac24-e87435256333-1.webp",
    "steps": 8,
    "format": "jpg",
    "prompt": "a nordic livingroom, 4k interior photography, uhd",
    "scheduler": "DDIM",
    "tile_size": 768,
    "creativity": 0.4,
    "guess_mode": false,
    "resolution": 2560,
    "resemblance": 0.85,
    "guidance_scale": 0,
    "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant",
    "lora_details_strength": -0.25,
    "lora_sharpness_strength": 0.75
  },
  "logs": "Using seed: 20941\nThe config attributes {'solver_order': 2, 'algorithm_type': 'deis', 'solver_type': 'logrho', 'lower_order_final': True, 'use_karras_sigmas': False} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  2.53it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  3.74it/s]\n100%|██████████| 3/3 [00:00<00:00,  4.42it/s]\n100%|██████████| 3/3 [00:00<00:00,  4.00it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.95it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  2.87it/s]\n100%|██████████| 3/3 [00:00<00:00,  3.39it/s]\n100%|██████████| 3/3 [00:00<00:00,  3.07it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.19it/s]\n 67%|██████▋   | 2/3 [00:01<00:00,  1.72it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.01it/s]\n100%|██████████| 3/3 [00:01<00:00,  1.83it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  3.68it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  5.52it/s]\n100%|██████████| 3/3 [00:00<00:00,  6.58it/s]\n100%|██████████| 3/3 [00:00<00:00,  5.92it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.96it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  2.89it/s]\n100%|██████████| 3/3 [00:00<00:00,  3.41it/s]\n100%|██████████| 3/3 [00:00<00:00,  3.09it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.52it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  2.22it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.60it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.36it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  3.60it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  5.34it/s]\n100%|██████████| 3/3 [00:00<00:00,  6.30it/s]\n100%|██████████| 3/3 [00:00<00:00,  5.70it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  9.58it/s]\n100%|██████████| 3/3 [00:00<00:00, 14.86it/s]\n100%|██████████| 3/3 [00:00<00:00, 14.07it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.76it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  2.59it/s]\n100%|██████████| 3/3 [00:01<00:00,  3.05it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.76it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  5.07it/s]\n100%|██████████| 3/3 [00:00<00:00,  8.61it/s]\n100%|██████████| 3/3 [00:00<00:00,  8.05it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.76it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  2.61it/s]\n100%|██████████| 3/3 [00:01<00:00,  3.08it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.78it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.34it/s]\n 67%|██████▋   | 2/3 [00:01<00:00,  1.95it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.28it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.08it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:01,  1.34it/s]\n 67%|██████▋   | 2/3 [00:01<00:00,  1.95it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.27it/s]\n100%|██████████| 3/3 [00:01<00:00,  2.07it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  4.06it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  6.06it/s]\n100%|██████████| 3/3 [00:00<00:00,  7.20it/s]\n100%|██████████| 3/3 [00:00<00:00,  6.49it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  4.88it/s]\n100%|██████████| 3/3 [00:00<00:00,  8.16it/s]\n100%|██████████| 3/3 [00:00<00:00,  7.65it/s]\n  0%|          | 0/3 [00:00<?, ?it/s]\n 33%|███▎      | 1/3 [00:00<00:00,  3.97it/s]\n 67%|██████▋   | 2/3 [00:00<00:00,  5.86it/s]\n100%|██████████| 3/3 [00:00<00:00,  6.92it/s]\n100%|██████████| 3/3 [00:00<00:00,  6.26it/s]\n  0%|          | 0/2 [00:00<?, ?it/s]\n 50%|█████     | 1/2 [00:03<00:03,  3.98s/it]\n100%|██████████| 2/2 [00:06<00:00,  2.94s/it]\n100%|██████████| 2/2 [00:06<00:00,  3.10s/it]",
  "metrics": {
    "predict_time": 59.897140822,
    "total_time": 133.557407
  },
  "output": "https://replicate.delivery/pbxt/YFlNVWt9oEpTMVEKg69wXDRGtjHSHKV02ESZeChKj69ffiYmA/output.jpg",
  "started_at": "2024-07-26T09:00:53.406266Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/4xg26j3bc9rgm0cgxs28xehaag",
    "cancel": "https://api.replicate.com/v1/predictions/4xg26j3bc9rgm0cgxs28xehaag/cancel"
  },
  "version": "13c637d35ebfe5e44a5297c370134b0f6921d0ee73f103ccfee7349dcaf59c76"
}

Generated in

59.9 seconds

Tweak it ShareReport

Using seed: 20941
The config attributes {'solver_order': 2, 'algorithm_type': 'deis', 'solver_type': 'logrho', 'lower_order_final': True, 'use_karras_sigmas': False} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  2.53it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  3.74it/s]
100%|██████████| 3/3 [00:00<00:00,  4.42it/s]
100%|██████████| 3/3 [00:00<00:00,  4.00it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.95it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  2.87it/s]
100%|██████████| 3/3 [00:00<00:00,  3.39it/s]
100%|██████████| 3/3 [00:00<00:00,  3.07it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.19it/s]
 67%|██████▋   | 2/3 [00:01<00:00,  1.72it/s]
100%|██████████| 3/3 [00:01<00:00,  2.01it/s]
100%|██████████| 3/3 [00:01<00:00,  1.83it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  3.68it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  5.52it/s]
100%|██████████| 3/3 [00:00<00:00,  6.58it/s]
100%|██████████| 3/3 [00:00<00:00,  5.92it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.96it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  2.89it/s]
100%|██████████| 3/3 [00:00<00:00,  3.41it/s]
100%|██████████| 3/3 [00:00<00:00,  3.09it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.52it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  2.22it/s]
100%|██████████| 3/3 [00:01<00:00,  2.60it/s]
100%|██████████| 3/3 [00:01<00:00,  2.36it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  3.60it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  5.34it/s]
100%|██████████| 3/3 [00:00<00:00,  6.30it/s]
100%|██████████| 3/3 [00:00<00:00,  5.70it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  9.58it/s]
100%|██████████| 3/3 [00:00<00:00, 14.86it/s]
100%|██████████| 3/3 [00:00<00:00, 14.07it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.76it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  2.59it/s]
100%|██████████| 3/3 [00:01<00:00,  3.05it/s]
100%|██████████| 3/3 [00:01<00:00,  2.76it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  5.07it/s]
100%|██████████| 3/3 [00:00<00:00,  8.61it/s]
100%|██████████| 3/3 [00:00<00:00,  8.05it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.76it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  2.61it/s]
100%|██████████| 3/3 [00:01<00:00,  3.08it/s]
100%|██████████| 3/3 [00:01<00:00,  2.78it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.34it/s]
 67%|██████▋   | 2/3 [00:01<00:00,  1.95it/s]
100%|██████████| 3/3 [00:01<00:00,  2.28it/s]
100%|██████████| 3/3 [00:01<00:00,  2.08it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.34it/s]
 67%|██████▋   | 2/3 [00:01<00:00,  1.95it/s]
100%|██████████| 3/3 [00:01<00:00,  2.27it/s]
100%|██████████| 3/3 [00:01<00:00,  2.07it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  4.06it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  6.06it/s]
100%|██████████| 3/3 [00:00<00:00,  7.20it/s]
100%|██████████| 3/3 [00:00<00:00,  6.49it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  4.88it/s]
100%|██████████| 3/3 [00:00<00:00,  8.16it/s]
100%|██████████| 3/3 [00:00<00:00,  7.65it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  3.97it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  5.86it/s]
100%|██████████| 3/3 [00:00<00:00,  6.92it/s]
100%|██████████| 3/3 [00:00<00:00,  6.26it/s]
  0%|          | 0/2 [00:00<?, ?it/s]
 50%|█████     | 1/2 [00:03<00:03,  3.98s/it]
100%|██████████| 2/2 [00:06<00:00,  2.94s/it]
100%|██████████| 2/2 [00:06<00:00,  3.10s/it]

This output was created using a different version of the model, fermatresearch/high-resolution-controlnet-tile:13c637d3.

Examples

View more examples

Run time and cost

This model costs approximately $0.045 to run on Replicate, or 22 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 47 seconds. The predict time for this model varies significantly based on the inputs.

Readme

High quality upscale from Fermat.app. Increase the creativity to encourage hallucination.