dhanushreddy291/sdvn10-anime – Run with an API on Replicate

dhanushreddy291 / sdvn10-anime

SDVN10-Anime

Cold

Public
335 runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,

Default: "child boy, short hair, crew neck sweater, (masterpiece, best quality:1.6), ghibli, Sun in the sky, Rocky Mountain National Park, Charismatic"

negative_prompt

string

Shift + Return to add a new line

watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)

Default: "(worst quality, normal quality, low quality, 3D, realistic:1.6)"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output

Default: 1

steps

integer

(minimum: 10, maximum: 100)

num_inference_steps

Default: 20

guidance

number

Guidance scale

Default: 7

scheduler

string

Choose a scheduler

Default: "EulerA"

width

integer

(minimum: 0, maximum: 1920)

Width

Default: 512

height

integer

(minimum: 0, maximum: 1920)

Height

Default: 728

seed

integer

Seed (0 = random, maximum: 2147483647)

Default: 0

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

npx create-replicate --model=dhanushreddy291/sdvn10-anime

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 dhanushreddy291/sdvn10-anime using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "dhanushreddy291/sdvn10-anime:ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951",
  {
    input: {
      seed: 0,
      steps: 34,
      width: 1024,
      height: 768,
      prompt: "lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,",
      guidance: 7,
      scheduler: "EulerA",
      num_outputs: 1,
      negative_prompt: "watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"
    }
  }
);
console.log(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 dhanushreddy291/sdvn10-anime using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "dhanushreddy291/sdvn10-anime:ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951",
    input={
        "seed": 0,
        "steps": 34,
        "width": 1024,
        "height": 768,
        "prompt": "lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,",
        "guidance": 7,
        "scheduler": "EulerA",
        "num_outputs": 1,
        "negative_prompt": "watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"
    }
)
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 dhanushreddy291/sdvn10-anime 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": "ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951",
    "input": {
      "seed": 0,
      "steps": 34,
      "width": 1024,
      "height": 768,
      "prompt": "lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,",
      "guidance": 7,
      "scheduler": "EulerA",
      "num_outputs": 1,
      "negative_prompt": "watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/dhanushreddy291/sdvn10-anime@sha256:ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951 \
  -i 'seed=0' \
  -i 'steps=34' \
  -i 'width=1024' \
  -i 'height=768' \
  -i 'prompt="lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,"' \
  -i 'guidance=7' \
  -i 'scheduler="EulerA"' \
  -i 'num_outputs=1' \
  -i 'negative_prompt="watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/dhanushreddy291/sdvn10-anime@sha256:ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 0,
      "steps": 34,
      "width": 1024,
      "height": 768,
      "prompt": "lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,",
      "guidance": 7,
      "scheduler": "EulerA",
      "num_outputs": 1,
      "negative_prompt": "watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-01-15T08:03:06.939709Z",
  "created_at": "2024-01-15T08:03:00.661613Z",
  "data_removed": false,
  "error": null,
  "id": "bgvzfqtbeqlqzjmhxn7c4mgmnm",
  "input": {
    "seed": 0,
    "steps": 34,
    "width": 1024,
    "height": 768,
    "prompt": "lady, sombre, (girl portrait:1.2), ((aodai:1.2)) , (masterpiece, best quality:1.6), , Snowing, Field of flowers, light, Eclectic,",
    "guidance": 7,
    "scheduler": "EulerA",
    "num_outputs": 1,
    "negative_prompt": "watermark,text, logo,contact, error, blurry, cropped, username, artist name, (worst quality, low quality,nsfw)"
  },
  "logs": "0%|          | 0/34 [00:00<?, ?it/s]\n  6%|▌         | 2/34 [00:00<00:02, 12.32it/s]\n 12%|█▏        | 4/34 [00:00<00:03,  8.89it/s]\n 15%|█▍        | 5/34 [00:00<00:03,  8.42it/s]\n 18%|█▊        | 6/34 [00:00<00:03,  8.12it/s]\n 21%|██        | 7/34 [00:00<00:03,  7.92it/s]\n 24%|██▎       | 8/34 [00:00<00:03,  7.77it/s]\n 26%|██▋       | 9/34 [00:01<00:03,  7.66it/s]\n 29%|██▉       | 10/34 [00:01<00:03,  7.59it/s]\n 32%|███▏      | 11/34 [00:01<00:03,  7.54it/s]\n 35%|███▌      | 12/34 [00:01<00:02,  7.51it/s]\n 38%|███▊      | 13/34 [00:01<00:02,  7.48it/s]\n 41%|████      | 14/34 [00:01<00:02,  7.47it/s]\n 44%|████▍     | 15/34 [00:01<00:02,  7.47it/s]\n 47%|████▋     | 16/34 [00:02<00:02,  7.45it/s]\n 50%|█████     | 17/34 [00:02<00:02,  7.44it/s]\n 53%|█████▎    | 18/34 [00:02<00:02,  7.43it/s]\n 56%|█████▌    | 19/34 [00:02<00:02,  7.43it/s]\n 59%|█████▉    | 20/34 [00:02<00:01,  7.43it/s]\n 62%|██████▏   | 21/34 [00:02<00:01,  7.42it/s]\n 65%|██████▍   | 22/34 [00:02<00:01,  7.42it/s]\n 68%|██████▊   | 23/34 [00:02<00:01,  7.44it/s]\n 71%|███████   | 24/34 [00:03<00:01,  7.43it/s]\n 74%|███████▎  | 25/34 [00:03<00:01,  7.41it/s]\n 76%|███████▋  | 26/34 [00:03<00:01,  7.41it/s]\n 79%|███████▉  | 27/34 [00:03<00:00,  7.41it/s]\n 82%|████████▏ | 28/34 [00:03<00:00,  7.41it/s]\n 85%|████████▌ | 29/34 [00:03<00:00,  7.41it/s]\n 88%|████████▊ | 30/34 [00:03<00:00,  7.41it/s]\n 91%|█████████ | 31/34 [00:04<00:00,  7.41it/s]\n 94%|█████████▍| 32/34 [00:04<00:00,  7.40it/s]\n 97%|█████████▋| 33/34 [00:04<00:00,  7.39it/s]\n100%|██████████| 34/34 [00:04<00:00,  7.39it/s]\n100%|██████████| 34/34 [00:04<00:00,  7.60it/s]",
  "metrics": {
    "predict_time": 6.233869,
    "total_time": 6.278096
  },
  "output": [
    "https://replicate.delivery/pbxt/JuLzwuhbl14PL9flxEpnNehDFq9hzct92nh3szh1YSx6ipMSA/out-0.png"
  ],
  "started_at": "2024-01-15T08:03:00.705840Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bgvzfqtbeqlqzjmhxn7c4mgmnm",
    "cancel": "https://api.replicate.com/v1/predictions/bgvzfqtbeqlqzjmhxn7c4mgmnm/cancel"
  },
  "version": "ce2ca6fd0837ffbd171a127f04ff7b8fe8cdf0f7ddc6739dd44409a758ded951"
}

Generated in

6.2 seconds

Tweak itReport

0%|          | 0/34 [00:00<?, ?it/s]
  6%|▌         | 2/34 [00:00<00:02, 12.32it/s]
 12%|█▏        | 4/34 [00:00<00:03,  8.89it/s]
 15%|█▍        | 5/34 [00:00<00:03,  8.42it/s]
 18%|█▊        | 6/34 [00:00<00:03,  8.12it/s]
 21%|██        | 7/34 [00:00<00:03,  7.92it/s]
 24%|██▎       | 8/34 [00:00<00:03,  7.77it/s]
 26%|██▋       | 9/34 [00:01<00:03,  7.66it/s]
 29%|██▉       | 10/34 [00:01<00:03,  7.59it/s]
 32%|███▏      | 11/34 [00:01<00:03,  7.54it/s]
 35%|███▌      | 12/34 [00:01<00:02,  7.51it/s]
 38%|███▊      | 13/34 [00:01<00:02,  7.48it/s]
 41%|████      | 14/34 [00:01<00:02,  7.47it/s]
 44%|████▍     | 15/34 [00:01<00:02,  7.47it/s]
 47%|████▋     | 16/34 [00:02<00:02,  7.45it/s]
 50%|█████     | 17/34 [00:02<00:02,  7.44it/s]
 53%|█████▎    | 18/34 [00:02<00:02,  7.43it/s]
 56%|█████▌    | 19/34 [00:02<00:02,  7.43it/s]
 59%|█████▉    | 20/34 [00:02<00:01,  7.43it/s]
 62%|██████▏   | 21/34 [00:02<00:01,  7.42it/s]
 65%|██████▍   | 22/34 [00:02<00:01,  7.42it/s]
 68%|██████▊   | 23/34 [00:02<00:01,  7.44it/s]
 71%|███████   | 24/34 [00:03<00:01,  7.43it/s]
 74%|███████▎  | 25/34 [00:03<00:01,  7.41it/s]
 76%|███████▋  | 26/34 [00:03<00:01,  7.41it/s]
 79%|███████▉  | 27/34 [00:03<00:00,  7.41it/s]
 82%|████████▏ | 28/34 [00:03<00:00,  7.41it/s]
 85%|████████▌ | 29/34 [00:03<00:00,  7.41it/s]
 88%|████████▊ | 30/34 [00:03<00:00,  7.41it/s]
 91%|█████████ | 31/34 [00:04<00:00,  7.41it/s]
 94%|█████████▍| 32/34 [00:04<00:00,  7.40it/s]
 97%|█████████▋| 33/34 [00:04<00:00,  7.39it/s]
100%|██████████| 34/34 [00:04<00:00,  7.39it/s]
100%|██████████| 34/34 [00:04<00:00,  7.60it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0061 to run on Replicate, or 163 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 7 seconds. The predict time for this model varies significantly based on the inputs.

Readme

SDVN10-Anime model from CivitAI. Credits to StableDiffusionVN (https://civitai.com/user/StableDiffusionVN) Model URL: https://civitai.com/models/254012/sdvn10-anime