asiryan/mistoon-anime-xl – Run with an API on Replicate

asiryan / mistoon-anime-xl

Mistoon Anime XL Model (Text2Img, Img2Img and Inpainting)

Cold

Public
19.1K runs
A100 (80GB)
GitHub

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, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewerscore_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer

Input prompt

Default: "score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer"

negative_prompt

string

Shift + Return to add a new line

score_6, score_5, score_4, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwearscore_6, score_5, score_4, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear

Negative Input prompt

Default: "score_6, score_5, score_4, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear"

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/mistoon-anime-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";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "asiryan/mistoon-anime-xl:06285a5017bb6bdc7314b3914c48896ffbe543ab8fa1ffc114f8894deac22c9d",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer",
      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, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear",
      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/mistoon-anime-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "asiryan/mistoon-anime-xl:06285a5017bb6bdc7314b3914c48896ffbe543ab8fa1ffc114f8894deac22c9d",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer",
        "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, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear",
        "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/mistoon-anime-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/mistoon-anime-xl:06285a5017bb6bdc7314b3914c48896ffbe543ab8fa1ffc114f8894deac22c9d",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer",
      "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, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear",
      "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": "2024-11-19T22:06:34.021257Z",
  "created_at": "2024-11-19T22:06:28.637000Z",
  "data_removed": false,
  "error": null,
  "id": "n4wjxb3n3nrj40ck8svbxr1qcw",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer",
    "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, multiple, lowres, text, error, missing arms, missing legs, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, out of frame, extra fingers, mutated hands, (poorly drawn hands), (poorly drawn face), (mutation), (deformed breasts), (ugly), blurry, (bad anatomy), (bad proportions), (extra limbs), cloned face, flat color, monochrome, limited palette, headwear",
    "num_inference_steps": 40
  },
  "logs": "Using seed: 35674\nPrompt: score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer\ntxt2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  5%|▌         | 2/40 [00:00<00:03, 11.66it/s]\n 10%|█         | 4/40 [00:00<00:03,  9.95it/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,  9.28it/s]\n 22%|██▎       | 9/40 [00:00<00:03,  9.21it/s]\n 25%|██▌       | 10/40 [00:01<00:03,  9.16it/s]\n 28%|██▊       | 11/40 [00:01<00:03,  9.12it/s]\n 30%|███       | 12/40 [00:01<00:03,  9.09it/s]\n 32%|███▎      | 13/40 [00:01<00:02,  9.07it/s]\n 35%|███▌      | 14/40 [00:01<00:02,  9.06it/s]\n 38%|███▊      | 15/40 [00:01<00:02,  9.05it/s]\n 40%|████      | 16/40 [00:01<00:02,  9.04it/s]\n 42%|████▎     | 17/40 [00:01<00:02,  9.04it/s]\n 45%|████▌     | 18/40 [00:01<00:02,  9.03it/s]\n 48%|████▊     | 19/40 [00:02<00:02,  9.03it/s]\n 50%|█████     | 20/40 [00:02<00:02,  9.03it/s]\n 52%|█████▎    | 21/40 [00:02<00:02,  9.03it/s]\n 55%|█████▌    | 22/40 [00:02<00:01,  9.03it/s]\n 57%|█████▊    | 23/40 [00:02<00:01,  9.03it/s]\n 60%|██████    | 24/40 [00:02<00:01,  9.03it/s]\n 62%|██████▎   | 25/40 [00:02<00:01,  9.02it/s]\n 65%|██████▌   | 26/40 [00:02<00:01,  9.02it/s]\n 68%|██████▊   | 27/40 [00:02<00:01,  9.02it/s]\n 70%|███████   | 28/40 [00:03<00:01,  9.02it/s]\n 72%|███████▎  | 29/40 [00:03<00:01,  9.02it/s]\n 75%|███████▌  | 30/40 [00:03<00:01,  9.02it/s]\n 78%|███████▊  | 31/40 [00:03<00:00,  9.02it/s]\n 80%|████████  | 32/40 [00:03<00:00,  9.02it/s]\n 82%|████████▎ | 33/40 [00:03<00:00,  9.02it/s]\n 85%|████████▌ | 34/40 [00:03<00:00,  9.02it/s]\n 88%|████████▊ | 35/40 [00:03<00:00,  9.02it/s]\n 90%|█████████ | 36/40 [00:03<00:00,  9.02it/s]\n 92%|█████████▎| 37/40 [00:04<00:00,  9.02it/s]\n 95%|█████████▌| 38/40 [00:04<00:00,  9.02it/s]\n 98%|█████████▊| 39/40 [00:04<00:00,  9.02it/s]\n100%|██████████| 40/40 [00:04<00:00,  9.02it/s]\n100%|██████████| 40/40 [00:04<00:00,  9.13it/s]",
  "metrics": {
    "predict_time": 5.371767951,
    "total_time": 5.384257
  },
  "output": [
    "https://replicate.delivery/yhqm/vY0apCOfejocb0h7OLybsRl0pdUEBBlbNEFdkxe8Z3WVvXlnA/out-0.png"
  ],
  "started_at": "2024-11-19T22:06:28.649489Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-g2zyqg2vdszwk2kfvs4jearsrd6nyiytuv77kbegcartupc3575q",
    "get": "https://api.replicate.com/v1/predictions/n4wjxb3n3nrj40ck8svbxr1qcw",
    "cancel": "https://api.replicate.com/v1/predictions/n4wjxb3n3nrj40ck8svbxr1qcw/cancel"
  },
  "version": "06285a5017bb6bdc7314b3914c48896ffbe543ab8fa1ffc114f8894deac22c9d"
}

Generated in

5.4 seconds

Tweak it ShareReport

Using seed: 35674
Prompt: score_9, score_8_up, score_7_up, karuizawa, 1girl, blonde hair, ponytail, hair scrunchie, blunt bangs, red eyes, blunt bangs, purple eyes, looking_at_viewer
txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  5%|▌         | 2/40 [00:00<00:03, 11.66it/s]
 10%|█         | 4/40 [00:00<00:03,  9.95it/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,  9.28it/s]
 22%|██▎       | 9/40 [00:00<00:03,  9.21it/s]
 25%|██▌       | 10/40 [00:01<00:03,  9.16it/s]
 28%|██▊       | 11/40 [00:01<00:03,  9.12it/s]
 30%|███       | 12/40 [00:01<00:03,  9.09it/s]
 32%|███▎      | 13/40 [00:01<00:02,  9.07it/s]
 35%|███▌      | 14/40 [00:01<00:02,  9.06it/s]
 38%|███▊      | 15/40 [00:01<00:02,  9.05it/s]
 40%|████      | 16/40 [00:01<00:02,  9.04it/s]
 42%|████▎     | 17/40 [00:01<00:02,  9.04it/s]
 45%|████▌     | 18/40 [00:01<00:02,  9.03it/s]
 48%|████▊     | 19/40 [00:02<00:02,  9.03it/s]
 50%|█████     | 20/40 [00:02<00:02,  9.03it/s]
 52%|█████▎    | 21/40 [00:02<00:02,  9.03it/s]
 55%|█████▌    | 22/40 [00:02<00:01,  9.03it/s]
 57%|█████▊    | 23/40 [00:02<00:01,  9.03it/s]
 60%|██████    | 24/40 [00:02<00:01,  9.03it/s]
 62%|██████▎   | 25/40 [00:02<00:01,  9.02it/s]
 65%|██████▌   | 26/40 [00:02<00:01,  9.02it/s]
 68%|██████▊   | 27/40 [00:02<00:01,  9.02it/s]
 70%|███████   | 28/40 [00:03<00:01,  9.02it/s]
 72%|███████▎  | 29/40 [00:03<00:01,  9.02it/s]
 75%|███████▌  | 30/40 [00:03<00:01,  9.02it/s]
 78%|███████▊  | 31/40 [00:03<00:00,  9.02it/s]
 80%|████████  | 32/40 [00:03<00:00,  9.02it/s]
 82%|████████▎ | 33/40 [00:03<00:00,  9.02it/s]
 85%|████████▌ | 34/40 [00:03<00:00,  9.02it/s]
 88%|████████▊ | 35/40 [00:03<00:00,  9.02it/s]
 90%|█████████ | 36/40 [00:03<00:00,  9.02it/s]
 92%|█████████▎| 37/40 [00:04<00:00,  9.02it/s]
 95%|█████████▌| 38/40 [00:04<00:00,  9.02it/s]
 98%|█████████▊| 39/40 [00:04<00:00,  9.02it/s]
100%|██████████| 40/40 [00:04<00:00,  9.02it/s]
100%|██████████| 40/40 [00:04<00:00,  9.13it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.052 to run on Replicate, or 19 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 37 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Mistoon Anime XL Model (Text2Img, Img2Img and Inpainting)