cottom/xsd_12kdsd | Run with an API on Replicate

cottom / xsd_12kdsd

(Updated 1 year, 8 months ago)

Cold

Public
208 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A photo of a room, 4k photo, highly detailedA photo of a room, 4k photo, highly detailed

Prompt to generate from

Default: ""

negative_prompt

string

Shift + Return to add a new line

anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfiguredanime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured

Prompt to generate from

Default: ""

image

*file

Preview

Grayscale input image

image_style_reference

file

Grayscale input image

scheduler

string

scheduler

Default: "K_EULER"

detect_resolution

integer

(minimum: 128, maximum: 4096)

Resolution at which detection method will be applied)

Default: 512

image_resolution

integer

(minimum: 128, maximum: 4096)

Resolution at which image will be applied)

Default: 1024

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of inference steps

Default: 30

guidance_scale

number

(minimum: 0, maximum: 10)

controlnet conditioning scale for generalization

Default: 2

num_images_per_prompt

integer

(minimum: 1, maximum: 9)

Number of image per prompt

Default: 1

condition_scale

number

(minimum: 0, maximum: 1)

controlnet conditioning scale for generalization

Default: 0.5

enable_depth_ctr

boolean

enable depth control

Default: true

enable_sketch_ctr

boolean

enable sketch control

Default: true

dry_run

boolean

dry run

Default: false

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

npx create-replicate --model=cottom/xsd_12kdsd

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";
import fs from "node:fs";

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

Run cottom/xsd_12kdsd using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cottom/xsd_12kdsd:84c5aa8681f48860a5a2adfa49f7b87cb2028494d847c690d4b6e6f77ab0f1f0",
  {
    input: {
      image: "https://replicate.delivery/pbxt/Jeys9hsouLzzzHHSLnCCiNU5httOBXz7uv5kEKLp7i440naF/output_0%20%281%29.png",
      prompt: "A photo of a room, 4k photo, highly detailed",
      dry_run: false,
      scheduler: "K_EULER",
      guidance_scale: 7.5,
      condition_scale: 1,
      negative_prompt: "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
      enable_depth_ctr: true,
      image_resolution: 1024,
      detect_resolution: 512,
      enable_sketch_ctr: true,
      num_inference_steps: 30,
      num_images_per_prompt: 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 cottom/xsd_12kdsd using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cottom/xsd_12kdsd:84c5aa8681f48860a5a2adfa49f7b87cb2028494d847c690d4b6e6f77ab0f1f0",
    input={
        "image": "https://replicate.delivery/pbxt/Jeys9hsouLzzzHHSLnCCiNU5httOBXz7uv5kEKLp7i440naF/output_0%20%281%29.png",
        "prompt": "A photo of a room, 4k photo, highly detailed",
        "dry_run": False,
        "scheduler": "K_EULER",
        "guidance_scale": 7.5,
        "condition_scale": 1,
        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
        "enable_depth_ctr": True,
        "image_resolution": 1024,
        "detect_resolution": 512,
        "enable_sketch_ctr": True,
        "num_inference_steps": 30,
        "num_images_per_prompt": 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 cottom/xsd_12kdsd 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": "cottom/xsd_12kdsd:84c5aa8681f48860a5a2adfa49f7b87cb2028494d847c690d4b6e6f77ab0f1f0",
    "input": {
      "image": "https://replicate.delivery/pbxt/Jeys9hsouLzzzHHSLnCCiNU5httOBXz7uv5kEKLp7i440naF/output_0%20%281%29.png",
      "prompt": "A photo of a room, 4k photo, highly detailed",
      "dry_run": false,
      "scheduler": "K_EULER",
      "guidance_scale": 7.5,
      "condition_scale": 1,
      "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
      "enable_depth_ctr": true,
      "image_resolution": 1024,
      "detect_resolution": 512,
      "enable_sketch_ctr": true,
      "num_inference_steps": 30,
      "num_images_per_prompt": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-10-07T21:11:27.728357Z",
  "created_at": "2023-10-07T21:04:10.447264Z",
  "data_removed": false,
  "error": null,
  "id": "ht73imlbuqeg4rsf4lmlgdhvq4",
  "input": {
    "image": "https://replicate.delivery/pbxt/Jeys9hsouLzzzHHSLnCCiNU5httOBXz7uv5kEKLp7i440naF/output_0%20%281%29.png",
    "prompt": "A photo of a room, 4k photo, highly detailed",
    "dry_run": false,
    "guidance_scale": 7.5,
    "condition_scale": 1,
    "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
    "enable_depth_ctr": true,
    "image_resolution": 1024,
    "detect_resolution": 512,
    "enable_sketch_ctr": true,
    "num_inference_steps": 30,
    "num_images_per_prompt": 1
  },
  "logs": "Run a single prediction on the model:\nOriginal width:1216, height:832\nAspect Ratio: 1.46\nresized width:1216, height:832\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:03,  8.43it/s]\n  7%|▋         | 2/30 [00:00<00:04,  6.59it/s]\n 10%|█         | 3/30 [00:00<00:04,  5.85it/s]\n 13%|█▎        | 4/30 [00:00<00:04,  5.55it/s]\n 17%|█▋        | 5/30 [00:00<00:04,  5.39it/s]\n 20%|██        | 6/30 [00:01<00:04,  5.29it/s]\n 23%|██▎       | 7/30 [00:01<00:04,  5.24it/s]\n 27%|██▋       | 8/30 [00:01<00:04,  5.21it/s]\n 30%|███       | 9/30 [00:01<00:04,  5.19it/s]\n 33%|███▎      | 10/30 [00:01<00:03,  5.17it/s]\n 37%|███▋      | 11/30 [00:02<00:03,  5.15it/s]\n 40%|████      | 12/30 [00:02<00:03,  5.14it/s]\n 43%|████▎     | 13/30 [00:02<00:03,  5.13it/s]\n 47%|████▋     | 14/30 [00:02<00:03,  5.13it/s]\n 50%|█████     | 15/30 [00:02<00:02,  5.12it/s]\n 53%|█████▎    | 16/30 [00:03<00:02,  5.12it/s]\n 57%|█████▋    | 17/30 [00:03<00:02,  5.11it/s]\n 60%|██████    | 18/30 [00:03<00:02,  5.11it/s]\n 63%|██████▎   | 19/30 [00:03<00:02,  5.11it/s]\n 67%|██████▋   | 20/30 [00:03<00:01,  5.11it/s]\n 70%|███████   | 21/30 [00:04<00:01,  5.11it/s]\n 73%|███████▎  | 22/30 [00:04<00:01,  5.11it/s]\n 77%|███████▋  | 23/30 [00:04<00:01,  5.11it/s]\n 80%|████████  | 24/30 [00:04<00:01,  5.11it/s]\n 83%|████████▎ | 25/30 [00:04<00:00,  5.11it/s]\n 87%|████████▋ | 26/30 [00:04<00:00,  5.11it/s]\n 90%|█████████ | 27/30 [00:05<00:00,  5.11it/s]\n 93%|█████████▎| 28/30 [00:05<00:00,  5.10it/s]\n 97%|█████████▋| 29/30 [00:05<00:00,  5.10it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.10it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.20it/s]",
  "metrics": {
    "predict_time": 15.493883,
    "total_time": 437.281093
  },
  "output": [
    "https://replicate.delivery/pbxt/H6AwCR2OI3raOFfj7rZRjBe1YYGrCbW1QNASdcb3Vg2ebvXjA/output_0.png"
  ],
  "started_at": "2023-10-07T21:11:12.234474Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ht73imlbuqeg4rsf4lmlgdhvq4",
    "cancel": "https://api.replicate.com/v1/predictions/ht73imlbuqeg4rsf4lmlgdhvq4/cancel"
  },
  "version": "275e48e44744c87d8062fcbec7c7f99be7b10b120a639ea9d3bb80ca0ce8b1d9"
}

Generated in

15.5 seconds

Tweak itReport

Run a single prediction on the model:
Original width:1216, height:832
Aspect Ratio: 1.46
resized width:1216, height:832
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:03,  8.43it/s]
  7%|▋         | 2/30 [00:00<00:04,  6.59it/s]
 10%|█         | 3/30 [00:00<00:04,  5.85it/s]
 13%|█▎        | 4/30 [00:00<00:04,  5.55it/s]
 17%|█▋        | 5/30 [00:00<00:04,  5.39it/s]
 20%|██        | 6/30 [00:01<00:04,  5.29it/s]
 23%|██▎       | 7/30 [00:01<00:04,  5.24it/s]
 27%|██▋       | 8/30 [00:01<00:04,  5.21it/s]
 30%|███       | 9/30 [00:01<00:04,  5.19it/s]
 33%|███▎      | 10/30 [00:01<00:03,  5.17it/s]
 37%|███▋      | 11/30 [00:02<00:03,  5.15it/s]
 40%|████      | 12/30 [00:02<00:03,  5.14it/s]
 43%|████▎     | 13/30 [00:02<00:03,  5.13it/s]
 47%|████▋     | 14/30 [00:02<00:03,  5.13it/s]
 50%|█████     | 15/30 [00:02<00:02,  5.12it/s]
 53%|█████▎    | 16/30 [00:03<00:02,  5.12it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  5.11it/s]
 60%|██████    | 18/30 [00:03<00:02,  5.11it/s]
 63%|██████▎   | 19/30 [00:03<00:02,  5.11it/s]
 67%|██████▋   | 20/30 [00:03<00:01,  5.11it/s]
 70%|███████   | 21/30 [00:04<00:01,  5.11it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  5.11it/s]
 77%|███████▋  | 23/30 [00:04<00:01,  5.11it/s]
 80%|████████  | 24/30 [00:04<00:01,  5.11it/s]
 83%|████████▎ | 25/30 [00:04<00:00,  5.11it/s]
 87%|████████▋ | 26/30 [00:04<00:00,  5.11it/s]
 90%|█████████ | 27/30 [00:05<00:00,  5.11it/s]
 93%|█████████▎| 28/30 [00:05<00:00,  5.10it/s]
 97%|█████████▋| 29/30 [00:05<00:00,  5.10it/s]
100%|██████████| 30/30 [00:05<00:00,  5.10it/s]
100%|██████████| 30/30 [00:05<00:00,  5.20it/s]

This output was created using a different version of the model, cottom/xsd_12kdsd:275e48e4.

Examples

View more examples

Run time and cost

This model costs approximately $0.031 to run on Replicate, or 32 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 33 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.