sontungpytn/genshin-ai-image-x – Run with an API on Replicate

sontungpytn / genshin-ai-image-x

Genshin Impact Image SD

Cold

Public
6.1K runs
T4

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

1girl, solo, umbrella, moonlight, city, butterfly, detail background1girl, solo, umbrella, moonlight, city, butterfly, detail background

Input prompt

Default: "1girl, solo, umbrella, moonlight, city, butterfly, detail background"

negative_prompt

string

Shift + Return to add a new line

paintings, sketches, fingers, (worst quality:2), (low quality:2)paintings, sketches, fingers, (worst quality:2), (low quality:2)

Input Negative Prompt

Default: "FastNegativeV2, EasyNegative, BadDream, paintings, sketches, bad hands, fingers, (worst quality:2), (low quality:2), 2girls, bad artist, text, error"

character

string

Genshin Impact character

Default: "raidenshogundef"

width

integer

Width of output image

Default: 512

height

integer

Height of output image

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 24

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7

seed

integer

Random seed. Leave blank to randomize the seed

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Default: false

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

npx create-replicate --model=sontungpytn/genshin-ai-image-x

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 sontungpytn/genshin-ai-image-x using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "sontungpytn/genshin-ai-image-x:2fabd9b0e3d54ece7ecf2a1d0ba21b9f150ad8c2d534d671e21d4741f1ced932",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "1girl, solo, umbrella, moonlight, city, butterfly, detail background",
      character: "raidenshogundef",
      scheduler: "K_EULER",
      num_outputs: 1,
      guidance_scale: 7,
      negative_prompt: "paintings, sketches, fingers, (worst quality:2), (low quality:2)",
      num_inference_steps: 24
    }
  }
);

// 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 sontungpytn/genshin-ai-image-x using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "sontungpytn/genshin-ai-image-x:2fabd9b0e3d54ece7ecf2a1d0ba21b9f150ad8c2d534d671e21d4741f1ced932",
    input={
        "width": 512,
        "height": 512,
        "prompt": "1girl, solo, umbrella, moonlight, city, butterfly, detail background",
        "character": "raidenshogundef",
        "scheduler": "K_EULER",
        "num_outputs": 1,
        "guidance_scale": 7,
        "negative_prompt": "paintings, sketches, fingers, (worst quality:2), (low quality:2)",
        "num_inference_steps": 24
    }
)
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 sontungpytn/genshin-ai-image-x 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": "sontungpytn/genshin-ai-image-x:2fabd9b0e3d54ece7ecf2a1d0ba21b9f150ad8c2d534d671e21d4741f1ced932",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "1girl, solo, umbrella, moonlight, city, butterfly, detail background",
      "character": "raidenshogundef",
      "scheduler": "K_EULER",
      "num_outputs": 1,
      "guidance_scale": 7,
      "negative_prompt": "paintings, sketches, fingers, (worst quality:2), (low quality:2)",
      "num_inference_steps": 24
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-16T19:02:05.514389Z",
  "created_at": "2023-11-16T18:59:16.706416Z",
  "data_removed": false,
  "error": null,
  "id": "fqksrsbbhhkziydz3xcgicglea",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "1girl, solo, umbrella, moonlight, city, butterfly, detail background",
    "character": "raidenshogundef",
    "scheduler": "K_EULER",
    "num_outputs": 1,
    "guidance_scale": 7,
    "negative_prompt": "paintings, sketches, fingers, (worst quality:2), (low quality:2)",
    "num_inference_steps": 24
  },
  "logs": "Using seed: 216732\n  0%|          | 0/24 [00:00<?, ?it/s]\n  4%|▍         | 1/24 [00:00<00:21,  1.07it/s]\n  8%|▊         | 2/24 [00:01<00:10,  2.06it/s]\n 12%|█▎        | 3/24 [00:01<00:07,  2.96it/s]\n 17%|█▋        | 4/24 [00:01<00:05,  3.73it/s]\n 21%|██        | 5/24 [00:01<00:04,  4.35it/s]\n 25%|██▌       | 6/24 [00:01<00:03,  4.83it/s]\n 29%|██▉       | 7/24 [00:01<00:03,  5.17it/s]\n 33%|███▎      | 8/24 [00:02<00:02,  5.42it/s]\n 38%|███▊      | 9/24 [00:02<00:02,  5.64it/s]\n 42%|████▏     | 10/24 [00:02<00:02,  5.80it/s]\n 46%|████▌     | 11/24 [00:02<00:02,  5.92it/s]\n 50%|█████     | 12/24 [00:02<00:01,  6.00it/s]\n 54%|█████▍    | 13/24 [00:02<00:01,  6.03it/s]\n 58%|█████▊    | 14/24 [00:03<00:01,  6.04it/s]\n 62%|██████▎   | 15/24 [00:03<00:01,  6.05it/s]\n 67%|██████▋   | 16/24 [00:03<00:01,  6.04it/s]\n 71%|███████   | 17/24 [00:03<00:01,  6.05it/s]\n 75%|███████▌  | 18/24 [00:03<00:00,  6.07it/s]\n 79%|███████▉  | 19/24 [00:03<00:00,  6.10it/s]\n 83%|████████▎ | 20/24 [00:04<00:00,  6.06it/s]\n 88%|████████▊ | 21/24 [00:04<00:00,  6.07it/s]\n 92%|█████████▏| 22/24 [00:04<00:00,  6.08it/s]\n 96%|█████████▌| 23/24 [00:04<00:00,  6.10it/s]\n100%|██████████| 24/24 [00:04<00:00,  6.11it/s]\n100%|██████████| 24/24 [00:04<00:00,  5.11it/s]",
  "metrics": {
    "predict_time": 6.850389,
    "total_time": 168.807973
  },
  "output": [
    "https://replicate.delivery/pbxt/fkciOob0IpxiKSDzItcxiGceShp9vsje43WXJVGbl4KZJDyjA/out-0.png"
  ],
  "started_at": "2023-11-16T19:01:58.664000Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fqksrsbbhhkziydz3xcgicglea",
    "cancel": "https://api.replicate.com/v1/predictions/fqksrsbbhhkziydz3xcgicglea/cancel"
  },
  "version": "bb775fc8060914b8baade7123a7ff41e9df8904aa129cf4517bd1bd5d8fa3b84"
}

Generated in

6.9 seconds

Tweak itReport

This output was created using a different version of the model, sontungpytn/genshin-ai-image-x:bb775fc8.

Examples

View more examples

Run time and cost

This model costs approximately $0.0056 to run on Replicate, or 178 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 T4 GPU hardware. Predictions typically complete within 25 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.