asiryan/2dn-xl – Run with an API on Replicate

asiryan / 2dn-xl

2DN XL Model (Text2Img, Img2Img and Inpainting)

Cold

Public
230 runs
A100 (80GB)
GitHub

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscapescore_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape

Input prompt

Default: "source_anime, score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up,(androgynous), ([1boy|1girl]), gender neutral, light purple hair, pastel colors, dark purple eyes, snow"

negative_prompt

string

Shift + Return to add a new line

score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyesscore_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes

Negative Input prompt

Default: "score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes"

image

file

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_ANCESTRAL"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 40

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 3.5

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

Including lora_scale and 1 more...

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

npx create-replicate --model=asiryan/2dn-xl

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 asiryan/2dn-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "asiryan/2dn-xl:b2ace84598c9fba90d498fdceb70506a36880464ec11c8e5dbf8008bcf325af4",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape",
      strength: 0.8,
      scheduler: "K_EULER_ANCESTRAL",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 3.5,
      negative_prompt: "score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes",
      num_inference_steps: 40
    }
  }
);

// 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 asiryan/2dn-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "asiryan/2dn-xl:b2ace84598c9fba90d498fdceb70506a36880464ec11c8e5dbf8008bcf325af4",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape",
        "strength": 0.8,
        "scheduler": "K_EULER_ANCESTRAL",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 3.5,
        "negative_prompt": "score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes",
        "num_inference_steps": 40
    }
)
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/2dn-xl 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": "asiryan/2dn-xl:b2ace84598c9fba90d498fdceb70506a36880464ec11c8e5dbf8008bcf325af4",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape",
      "strength": 0.8,
      "scheduler": "K_EULER_ANCESTRAL",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 3.5,
      "negative_prompt": "score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes",
      "num_inference_steps": 40
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-19T22:29:31.938943Z",
  "created_at": "2024-11-19T22:29:26.522000Z",
  "data_removed": false,
  "error": null,
  "id": "y38qeekvf9rj60ck8t5vpesn34",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape",
    "strength": 0.8,
    "scheduler": "K_EULER_ANCESTRAL",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 3.5,
    "negative_prompt": "score_6, score_5, score_4, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, poorly drawn face, ugly face, crossed eyes",
    "num_inference_steps": 40
  },
  "logs": "Using seed: 52478\nPrompt: score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape\ntxt2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  5%|▌         | 2/40 [00:00<00:03, 11.62it/s]\n 10%|█         | 4/40 [00:00<00:03,  9.92it/s]\n 15%|█▌        | 6/40 [00:00<00:03,  9.49it/s]\n 18%|█▊        | 7/40 [00:00<00:03,  9.37it/s]\n 20%|██        | 8/40 [00:00<00:03,  9.27it/s]\n 22%|██▎       | 9/40 [00:00<00:03,  9.20it/s]\n 25%|██▌       | 10/40 [00:01<00:03,  9.15it/s]\n 28%|██▊       | 11/40 [00:01<00:03,  9.08it/s]\n 30%|███       | 12/40 [00:01<00:03,  9.04it/s]\n 32%|███▎      | 13/40 [00:01<00:02,  9.01it/s]\n 35%|███▌      | 14/40 [00:01<00:02,  9.01it/s]\n 38%|███▊      | 15/40 [00:01<00:02,  9.01it/s]\n 40%|████      | 16/40 [00:01<00:02,  8.99it/s]\n 42%|████▎     | 17/40 [00:01<00:02,  8.97it/s]\n 45%|████▌     | 18/40 [00:01<00:02,  8.96it/s]\n 48%|████▊     | 19/40 [00:02<00:02,  8.95it/s]\n 50%|█████     | 20/40 [00:02<00:02,  8.94it/s]\n 52%|█████▎    | 21/40 [00:02<00:02,  8.94it/s]\n 55%|█████▌    | 22/40 [00:02<00:02,  8.93it/s]\n 57%|█████▊    | 23/40 [00:02<00:01,  8.93it/s]\n 60%|██████    | 24/40 [00:02<00:01,  8.93it/s]\n 62%|██████▎   | 25/40 [00:02<00:01,  8.93it/s]\n 65%|██████▌   | 26/40 [00:02<00:01,  8.93it/s]\n 68%|██████▊   | 27/40 [00:02<00:01,  8.93it/s]\n 70%|███████   | 28/40 [00:03<00:01,  8.93it/s]\n 72%|███████▎  | 29/40 [00:03<00:01,  8.93it/s]\n 75%|███████▌  | 30/40 [00:03<00:01,  8.93it/s]\n 78%|███████▊  | 31/40 [00:03<00:01,  8.93it/s]\n 80%|████████  | 32/40 [00:03<00:00,  8.93it/s]\n 82%|████████▎ | 33/40 [00:03<00:00,  8.93it/s]\n 85%|████████▌ | 34/40 [00:03<00:00,  8.93it/s]\n 88%|████████▊ | 35/40 [00:03<00:00,  8.93it/s]\n 90%|█████████ | 36/40 [00:03<00:00,  8.93it/s]\n 92%|█████████▎| 37/40 [00:04<00:00,  8.93it/s]\n 95%|█████████▌| 38/40 [00:04<00:00,  8.92it/s]\n 98%|█████████▊| 39/40 [00:04<00:00,  8.92it/s]\n100%|██████████| 40/40 [00:04<00:00,  8.93it/s]\n100%|██████████| 40/40 [00:04<00:00,  9.05it/s]",
  "metrics": {
    "predict_time": 5.402008228,
    "total_time": 5.416943
  },
  "output": [
    "https://replicate.delivery/yhqm/HSIG9fNJQ4WfgkVMDAZZU8Ee6TWcChNd83WL7kB5lFtXaYlnA/out-0.png"
  ],
  "started_at": "2024-11-19T22:29:26.536934Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-v55wav4bt7j5it2knz6a26z2er3ohlxpovz7tntoge5xnnirafla",
    "get": "https://api.replicate.com/v1/predictions/y38qeekvf9rj60ck8t5vpesn34",
    "cancel": "https://api.replicate.com/v1/predictions/y38qeekvf9rj60ck8t5vpesn34/cancel"
  },
  "version": "b2ace84598c9fba90d498fdceb70506a36880464ec11c8e5dbf8008bcf325af4"
}

Generated in

5.4 seconds

Tweak it ShareReport

Using seed: 52478
Prompt: score_9, score_8_up, score_7_up, score_6_up, source_anime, masterpiece, newest, neutrofil land, cube, iridescent geometry, forest, reflections, sky, outdoors, landscape
txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  5%|▌         | 2/40 [00:00<00:03, 11.62it/s]
 10%|█         | 4/40 [00:00<00:03,  9.92it/s]
 15%|█▌        | 6/40 [00:00<00:03,  9.49it/s]
 18%|█▊        | 7/40 [00:00<00:03,  9.37it/s]
 20%|██        | 8/40 [00:00<00:03,  9.27it/s]
 22%|██▎       | 9/40 [00:00<00:03,  9.20it/s]
 25%|██▌       | 10/40 [00:01<00:03,  9.15it/s]
 28%|██▊       | 11/40 [00:01<00:03,  9.08it/s]
 30%|███       | 12/40 [00:01<00:03,  9.04it/s]
 32%|███▎      | 13/40 [00:01<00:02,  9.01it/s]
 35%|███▌      | 14/40 [00:01<00:02,  9.01it/s]
 38%|███▊      | 15/40 [00:01<00:02,  9.01it/s]
 40%|████      | 16/40 [00:01<00:02,  8.99it/s]
 42%|████▎     | 17/40 [00:01<00:02,  8.97it/s]
 45%|████▌     | 18/40 [00:01<00:02,  8.96it/s]
 48%|████▊     | 19/40 [00:02<00:02,  8.95it/s]
 50%|█████     | 20/40 [00:02<00:02,  8.94it/s]
 52%|█████▎    | 21/40 [00:02<00:02,  8.94it/s]
 55%|█████▌    | 22/40 [00:02<00:02,  8.93it/s]
 57%|█████▊    | 23/40 [00:02<00:01,  8.93it/s]
 60%|██████    | 24/40 [00:02<00:01,  8.93it/s]
 62%|██████▎   | 25/40 [00:02<00:01,  8.93it/s]
 65%|██████▌   | 26/40 [00:02<00:01,  8.93it/s]
 68%|██████▊   | 27/40 [00:02<00:01,  8.93it/s]
 70%|███████   | 28/40 [00:03<00:01,  8.93it/s]
 72%|███████▎  | 29/40 [00:03<00:01,  8.93it/s]
 75%|███████▌  | 30/40 [00:03<00:01,  8.93it/s]
 78%|███████▊  | 31/40 [00:03<00:01,  8.93it/s]
 80%|████████  | 32/40 [00:03<00:00,  8.93it/s]
 82%|████████▎ | 33/40 [00:03<00:00,  8.93it/s]
 85%|████████▌ | 34/40 [00:03<00:00,  8.93it/s]
 88%|████████▊ | 35/40 [00:03<00:00,  8.93it/s]
 90%|█████████ | 36/40 [00:03<00:00,  8.93it/s]
 92%|█████████▎| 37/40 [00:04<00:00,  8.93it/s]
 95%|█████████▌| 38/40 [00:04<00:00,  8.92it/s]
 98%|█████████▊| 39/40 [00:04<00:00,  8.92it/s]
100%|██████████| 40/40 [00:04<00:00,  8.93it/s]
100%|██████████| 40/40 [00:04<00:00,  9.05it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0066 to run on Replicate, or 151 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 A100 (80GB) GPU hardware. Predictions typically complete within 5 seconds.

Readme

2DN XL Model (Text2Img, Img2Img and Inpainting)