adarshnagrikar14/manhwa-ai | Run with an API on Replicate

adarshnagrikar14 / manhwa-ai

(Updated 1 month, 2 weeks ago)

Cold

Public
511 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

input_image

*file

Input image for editing and subject conditioning

inpainting_mask

*file

Inpainting mask image (white areas will be inpainted)

expression

string

Shift + Return to add a new line

Desired facial expression for the manhwa style (e.g., 'happy', 'angry', 'surprised', 'neutral')

Default: "k-drama happy, confident, smiling"

height

integer

Height of the output image

Default: 768

width

integer

Width of the output image

Default: 512

seed

integer

Random seed

Default: 42

subject_lora_scale

number

(minimum: 0, maximum: 2)

Scale for the Subject LoRA weights

Default: 1

inpainting_lora_scale

number

(minimum: 0, maximum: 2)

Scale for the Inpainting LoRA weights

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 16

cond_size

integer

(minimum: 512, maximum: 1024)

Conditioning size

Default: 512

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

npx create-replicate --model=adarshnagrikar14/manhwa-ai

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 adarshnagrikar14/manhwa-ai using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adarshnagrikar14/manhwa-ai:2cfc253b2070af68f932afced7959b05de1e4ec800200ef945f338d3c289a8a1",
  {
    input: {
      seed: 42,
      width: 768,
      height: 768,
      cond_size: 512,
      expression: "k-drama happy, confident, smiling",
      subject_lora_scale: 1,
      num_inference_steps: 16,
      inpainting_lora_scale: 1
    }
  }
);

// 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 adarshnagrikar14/manhwa-ai using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adarshnagrikar14/manhwa-ai:2cfc253b2070af68f932afced7959b05de1e4ec800200ef945f338d3c289a8a1",
    input={
        "seed": 42,
        "width": 768,
        "height": 768,
        "cond_size": 512,
        "expression": "k-drama happy, confident, smiling",
        "subject_lora_scale": 1,
        "num_inference_steps": 16,
        "inpainting_lora_scale": 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 adarshnagrikar14/manhwa-ai 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": "adarshnagrikar14/manhwa-ai:2cfc253b2070af68f932afced7959b05de1e4ec800200ef945f338d3c289a8a1",
    "input": {
      "seed": 42,
      "width": 768,
      "height": 768,
      "cond_size": 512,
      "expression": "k-drama happy, confident, smiling",
      "subject_lora_scale": 1,
      "num_inference_steps": 16,
      "inpainting_lora_scale": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-04-22T10:00:50.174308Z",
  "created_at": "2025-04-22T09:59:37.854000Z",
  "data_removed": false,
  "error": null,
  "id": "gv4z2fjtfsrj40cpbkr83ts6w0",
  "input": {
    "seed": 42,
    "width": 768,
    "height": 768,
    "prompt": "Turn this bald, brown-skinned man with a long gray beard and glasses into a K-pop manhwa-style character. Maintain strong facial resemblance: his round head shape, thick beard (styled smoothly and sharply like a pop icon), and glasses — but update the frames to look modern and sleek. Make his eyes expressive and charismatic, classic manhwa style but still grounded in realism. Give him a bright smile and clean, glowing skin. Dress him in a black, stylish performance outfit with layered silver chains and rings. Place a vibrant K-pop stage in the background with red neon lights and dramatic spotlights for a high-energy performance vibe. Emphasize idol confidence and coolness while preserving the original character and facial features.",
    "lora_scale": 1,
    "spatial_img": "https://vzgwpzccjffstvxfjqvq.supabase.co/storage/v1/object/public/burger-king/user-uploads/mnk-1745315968473-user.png",
    "control_type": "Manhwa"
  },
  "logs": "Loading .safetensors checkpoint from ./models/studio.safetensors\nToken indices sequence length is longer than the specified maximum sequence length for this model (149 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['in realism. give him a bright smile and clean, glowing skin. dress him in a black, stylish performance outfit with layered silver chains and rings. place a vibrant k - pop stage in the background with red neon lights and dramatic spotlights for a high - energy performance vibe. emphasize idol confidence and coolness while preserving the original character and facial features.']\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:17,  2.28it/s]\n  5%|▌         | 2/40 [00:00<00:13,  2.73it/s]\n  8%|▊         | 3/40 [00:01<00:14,  2.55it/s]\n 10%|█         | 4/40 [00:01<00:14,  2.48it/s]\n 12%|█▎        | 5/40 [00:02<00:14,  2.43it/s]\n 15%|█▌        | 6/40 [00:02<00:14,  2.41it/s]\n 18%|█▊        | 7/40 [00:02<00:13,  2.40it/s]\n 20%|██        | 8/40 [00:03<00:13,  2.38it/s]\n 22%|██▎       | 9/40 [00:03<00:13,  2.38it/s]\n 25%|██▌       | 10/40 [00:04<00:12,  2.37it/s]\n 28%|██▊       | 11/40 [00:04<00:12,  2.37it/s]\n 30%|███       | 12/40 [00:04<00:11,  2.37it/s]\n 32%|███▎      | 13/40 [00:05<00:11,  2.37it/s]\n 35%|███▌      | 14/40 [00:05<00:11,  2.36it/s]\n 38%|███▊      | 15/40 [00:06<00:10,  2.36it/s]\n 40%|████      | 16/40 [00:06<00:10,  2.36it/s]\n 42%|████▎     | 17/40 [00:07<00:09,  2.36it/s]\n 45%|████▌     | 18/40 [00:07<00:09,  2.36it/s]\n 48%|████▊     | 19/40 [00:07<00:08,  2.36it/s]\n 50%|█████     | 20/40 [00:08<00:08,  2.36it/s]\n 52%|█████▎    | 21/40 [00:08<00:08,  2.36it/s]\n 55%|█████▌    | 22/40 [00:09<00:07,  2.36it/s]\n 57%|█████▊    | 23/40 [00:09<00:07,  2.36it/s]\n 60%|██████    | 24/40 [00:10<00:06,  2.36it/s]\n 62%|██████▎   | 25/40 [00:10<00:06,  2.36it/s]\n 65%|██████▌   | 26/40 [00:10<00:05,  2.36it/s]\n 68%|██████▊   | 27/40 [00:11<00:05,  2.36it/s]\n 70%|███████   | 28/40 [00:11<00:05,  2.36it/s]\n 72%|███████▎  | 29/40 [00:12<00:04,  2.36it/s]\n 75%|███████▌  | 30/40 [00:12<00:04,  2.36it/s]\n 78%|███████▊  | 31/40 [00:13<00:03,  2.36it/s]\n 80%|████████  | 32/40 [00:13<00:03,  2.36it/s]\n 82%|████████▎ | 33/40 [00:13<00:02,  2.36it/s]\n 85%|████████▌ | 34/40 [00:14<00:02,  2.36it/s]\n 88%|████████▊ | 35/40 [00:14<00:02,  2.36it/s]\n 90%|█████████ | 36/40 [00:15<00:01,  2.36it/s]\n 92%|█████████▎| 37/40 [00:15<00:01,  2.36it/s]\n 95%|█████████▌| 38/40 [00:16<00:00,  2.36it/s]\n 98%|█████████▊| 39/40 [00:16<00:00,  2.36it/s]\n100%|██████████| 40/40 [00:16<00:00,  2.36it/s]\n100%|██████████| 40/40 [00:16<00:00,  2.37it/s]",
  "metrics": {
    "predict_time": 21.058624843,
    "total_time": 72.320308
  },
  "output": "https://replicate.delivery/yhqm/xmR12MQEzZpBOJ7aykRvcqRfsqDCiaQ3dx87HKOtzGJp1oSKA/output.png",
  "started_at": "2025-04-22T10:00:29.115683Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-up5y4fnidxl6of5izcz6ww6hlqvjv5vjbswakdvssmmrkgyabztq",
    "get": "https://api.replicate.com/v1/predictions/gv4z2fjtfsrj40cpbkr83ts6w0",
    "cancel": "https://api.replicate.com/v1/predictions/gv4z2fjtfsrj40cpbkr83ts6w0/cancel"
  },
  "version": "8329635110a64e8112d8f287956349d09f140750df462dcb35d8aa2be2873670"
}

Generated in

21.1 seconds

Tweak it ShareReport View full prediction

Loading .safetensors checkpoint from ./models/studio.safetensors
Token indices sequence length is longer than the specified maximum sequence length for this model (149 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['in realism. give him a bright smile and clean, glowing skin. dress him in a black, stylish performance outfit with layered silver chains and rings. place a vibrant k - pop stage in the background with red neon lights and dramatic spotlights for a high - energy performance vibe. emphasize idol confidence and coolness while preserving the original character and facial features.']
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:17,  2.28it/s]
  5%|▌         | 2/40 [00:00<00:13,  2.73it/s]
  8%|▊         | 3/40 [00:01<00:14,  2.55it/s]
 10%|█         | 4/40 [00:01<00:14,  2.48it/s]
 12%|█▎        | 5/40 [00:02<00:14,  2.43it/s]
 15%|█▌        | 6/40 [00:02<00:14,  2.41it/s]
 18%|█▊        | 7/40 [00:02<00:13,  2.40it/s]
 20%|██        | 8/40 [00:03<00:13,  2.38it/s]
 22%|██▎       | 9/40 [00:03<00:13,  2.38it/s]
 25%|██▌       | 10/40 [00:04<00:12,  2.37it/s]
 28%|██▊       | 11/40 [00:04<00:12,  2.37it/s]
 30%|███       | 12/40 [00:04<00:11,  2.37it/s]
 32%|███▎      | 13/40 [00:05<00:11,  2.37it/s]
 35%|███▌      | 14/40 [00:05<00:11,  2.36it/s]
 38%|███▊      | 15/40 [00:06<00:10,  2.36it/s]
 40%|████      | 16/40 [00:06<00:10,  2.36it/s]
 42%|████▎     | 17/40 [00:07<00:09,  2.36it/s]
 45%|████▌     | 18/40 [00:07<00:09,  2.36it/s]
 48%|████▊     | 19/40 [00:07<00:08,  2.36it/s]
 50%|█████     | 20/40 [00:08<00:08,  2.36it/s]
 52%|█████▎    | 21/40 [00:08<00:08,  2.36it/s]
 55%|█████▌    | 22/40 [00:09<00:07,  2.36it/s]
 57%|█████▊    | 23/40 [00:09<00:07,  2.36it/s]
 60%|██████    | 24/40 [00:10<00:06,  2.36it/s]
 62%|██████▎   | 25/40 [00:10<00:06,  2.36it/s]
 65%|██████▌   | 26/40 [00:10<00:05,  2.36it/s]
 68%|██████▊   | 27/40 [00:11<00:05,  2.36it/s]
 70%|███████   | 28/40 [00:11<00:05,  2.36it/s]
 72%|███████▎  | 29/40 [00:12<00:04,  2.36it/s]
 75%|███████▌  | 30/40 [00:12<00:04,  2.36it/s]
 78%|███████▊  | 31/40 [00:13<00:03,  2.36it/s]
 80%|████████  | 32/40 [00:13<00:03,  2.36it/s]
 82%|████████▎ | 33/40 [00:13<00:02,  2.36it/s]
 85%|████████▌ | 34/40 [00:14<00:02,  2.36it/s]
 88%|████████▊ | 35/40 [00:14<00:02,  2.36it/s]
 90%|█████████ | 36/40 [00:15<00:01,  2.36it/s]
 92%|█████████▎| 37/40 [00:15<00:01,  2.36it/s]
 95%|█████████▌| 38/40 [00:16<00:00,  2.36it/s]
 98%|█████████▊| 39/40 [00:16<00:00,  2.36it/s]
100%|██████████| 40/40 [00:16<00:00,  2.36it/s]
100%|██████████| 40/40 [00:16<00:00,  2.37it/s]

This output was created using a different version of the model, adarshnagrikar14/manhwa-ai:83296351.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.