asiryan/deliberate-v3 – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Input prompt

Default: "mj, ny, cinematic"

negative_prompt

string

Shift + Return to add a new line

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

Input Negative Prompt

Default: "[deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

image

file

Input image for img2img and inpainting modes

mask

file

Mask image for inpainting mode

width

integer

(minimum: 0, maximum: 1920)

Width

Default: 512

height

integer

(minimum: 0, maximum: 1920)

Height

Default: 728

strength

number

(minimum: 0, maximum: 1)

Strength/weight

Default: 1

num_inference_steps

integer

(minimum: 0, maximum: 100)

Number of inference steps

Default: 20

guidance_scale

number

(minimum: 0, maximum: 10)

Guidance scale

Default: 7.5

scheduler

string

Scheduler

Default: "K_EULER_ANCESTRAL"

use_karras_sigmas

boolean

Use karras sigmas or not

Default: false

seed

integer

Leave blank to randomize

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

npx create-replicate --model=asiryan/deliberate-v3

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 asiryan/deliberate-v3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "asiryan/deliberate-v3:b6739c3d471044fff87be8f0310b322c61833930ce720418d4bb26499b3a82ea",
  {
    input: {
      width: 512,
      height: 728,
      prompt: "mj, ny, cinematic",
      strength: 1,
      scheduler: "K_EULER_ANCESTRAL",
      guidance_scale: 7.5,
      negative_prompt: "[deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      use_karras_sigmas: false,
      num_inference_steps: 20
    }
  }
);

// 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 asiryan/deliberate-v3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "asiryan/deliberate-v3:b6739c3d471044fff87be8f0310b322c61833930ce720418d4bb26499b3a82ea",
    input={
        "width": 512,
        "height": 728,
        "prompt": "mj, ny, cinematic",
        "strength": 1,
        "scheduler": "K_EULER_ANCESTRAL",
        "guidance_scale": 7.5,
        "negative_prompt": "[deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "use_karras_sigmas": False,
        "num_inference_steps": 20
    }
)
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 asiryan/deliberate-v3 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": "b6739c3d471044fff87be8f0310b322c61833930ce720418d4bb26499b3a82ea",
    "input": {
      "width": 512,
      "height": 728,
      "prompt": "mj, ny, cinematic",
      "strength": 1,
      "scheduler": "K_EULER_ANCESTRAL",
      "guidance_scale": 7.5,
      "negative_prompt": "[deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "use_karras_sigmas": false,
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-27T02:55:23.573466Z",
  "created_at": "2023-11-27T02:54:11.591889Z",
  "data_removed": false,
  "error": null,
  "id": "zq2j7u3bgjozdmptzelav5tefq",
  "input": {
    "width": 512,
    "height": 728,
    "prompt": "mj, ny, cinematic",
    "strength": 1,
    "scheduler": "K_EULER_ANCESTRAL",
    "guidance_scale": 7.5,
    "negative_prompt": "[deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
    "use_karras_sigmas": false,
    "num_inference_steps": 20
  },
  "logs": "Scheduler: K_EULER_ANCESTRAL\nUsing karras sigmas: False\nUsing seed: 20529\nMode: text2img\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:11,  1.71it/s]\n 10%|█         | 2/20 [00:00<00:05,  3.01it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  3.97it/s]\n 20%|██        | 4/20 [00:01<00:03,  4.67it/s]\n 25%|██▌       | 5/20 [00:01<00:02,  5.18it/s]\n 30%|███       | 6/20 [00:01<00:02,  5.53it/s]\n 35%|███▌      | 7/20 [00:01<00:02,  5.78it/s]\n 40%|████      | 8/20 [00:01<00:02,  5.96it/s]\n 45%|████▌     | 9/20 [00:01<00:01,  6.08it/s]\n 50%|█████     | 10/20 [00:01<00:01,  6.17it/s]\n 55%|█████▌    | 11/20 [00:02<00:01,  6.23it/s]\n 60%|██████    | 12/20 [00:02<00:01,  6.27it/s]\n 65%|██████▌   | 13/20 [00:02<00:01,  6.30it/s]\n 70%|███████   | 14/20 [00:02<00:00,  6.32it/s]\n 75%|███████▌  | 15/20 [00:02<00:00,  6.33it/s]\n 80%|████████  | 16/20 [00:02<00:00,  6.35it/s]\n 85%|████████▌ | 17/20 [00:03<00:00,  6.36it/s]\n 90%|█████████ | 18/20 [00:03<00:00,  6.38it/s]\n 95%|█████████▌| 19/20 [00:03<00:00,  6.38it/s]\n100%|██████████| 20/20 [00:03<00:00,  6.39it/s]\n100%|██████████| 20/20 [00:03<00:00,  5.62it/s]",
  "metrics": {
    "predict_time": 5.401556,
    "total_time": 71.981577
  },
  "output": "https://replicate.delivery/pbxt/tQOUeppfKXjDtkSh3h2Y8EseCFUmv5mM77NS7GNKcgx1424jA/output.png",
  "started_at": "2023-11-27T02:55:18.171910Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zq2j7u3bgjozdmptzelav5tefq",
    "cancel": "https://api.replicate.com/v1/predictions/zq2j7u3bgjozdmptzelav5tefq/cancel"
  },
  "version": "b6739c3d471044fff87be8f0310b322c61833930ce720418d4bb26499b3a82ea"
}

Generated in

5.4 seconds

Tweak itReport

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.