charlesmccarthy/anima_pencil-xl – Run with an API on Replicate

charlesmccarthy / anima_pencil-xl

blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1, The top ranked model on Civitai

Cold

Public
3.6K runs
L40S

Run with an API

Playground API Examples README Versions

Input

model

string

The model to use

Default: "Anima_Pencil-XL-v4.safetensors"

vae

string

The VAE to use

Default: "sdxl-vae-fp16-fix"

prompt

string

Shift + Return to add a new line

1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset

The prompt

Default: "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset"

negative_prompt

string

Shift + Return to add a new line

unaestheticXL_Sky3.1, animal, cat, dog, big breastsunaestheticXL_Sky3.1, animal, cat, dog, big breasts

The negative prompt (For things you don't want)

Default: "unaestheticXL_Sky3.1, animal, cat, dog, big breasts"

scheduler

string

The scheduler to use

Default: "DPM++ 2M SDE Karras"

steps

integer

(minimum: 1, maximum: 100)

The steps when generating

Default: 35

cfg_scale

number

(minimum: 1, maximum: 30)

CFG Scale defines how much attention the model pays to the prompt when generating

Default: 7

guidance_rescale

number

(minimum: 0, maximum: 1)

The amount to rescale CFG generated noise to avoid generating overexposed images

Default: 0.7

width

integer

(minimum: 1, maximum: 2048)

The width of the image

Default: 1184

height

integer

(minimum: 1, maximum: 2048)

The height of the image

Default: 864

batch_size

integer

(minimum: 1, maximum: 4)

Number of images to generate (1-4)

Default: 1

seed

integer

The seed used when generating, set to -1 for random seed

Default: -1

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

npx create-replicate --model=charlesmccarthy/anima_pencil-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 charlesmccarthy/anima_pencil-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "charlesmccarthy/anima_pencil-xl:7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3",
  {
    input: {
      vae: "sdxl-vae-fp16-fix",
      seed: -1,
      model: "Anima_Pencil-XL-v4.safetensors",
      steps: 35,
      width: 1184,
      height: 864,
      prompt: "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
      cfg_scale: 7,
      scheduler: "DPM++ 2M SDE Karras",
      batch_size: 1,
      negative_prompt: "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
      guidance_rescale: 0.7
    }
  }
);
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 charlesmccarthy/anima_pencil-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "charlesmccarthy/anima_pencil-xl:7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3",
    input={
        "vae": "sdxl-vae-fp16-fix",
        "seed": -1,
        "model": "Anima_Pencil-XL-v4.safetensors",
        "steps": 35,
        "width": 1184,
        "height": 864,
        "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
        "cfg_scale": 7,
        "scheduler": "DPM++ 2M SDE Karras",
        "batch_size": 1,
        "negative_prompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
        "guidance_rescale": 0.7
    }
)
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 charlesmccarthy/anima_pencil-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": "7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3",
    "input": {
      "vae": "sdxl-vae-fp16-fix",
      "seed": -1,
      "model": "Anima_Pencil-XL-v4.safetensors",
      "steps": 35,
      "width": 1184,
      "height": 864,
      "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
      "cfg_scale": 7,
      "scheduler": "DPM++ 2M SDE Karras",
      "batch_size": 1,
      "negative_prompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
      "guidance_rescale": 0.7
    }
  }' \
  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/charlesmccarthy/anima_pencil-xl@sha256:7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3 \
  -i 'vae="sdxl-vae-fp16-fix"' \
  -i 'seed=-1' \
  -i 'model="Anima_Pencil-XL-v4.safetensors"' \
  -i 'steps=35' \
  -i 'width=1184' \
  -i 'height=864' \
  -i 'prompt="1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset"' \
  -i 'cfg_scale=7' \
  -i 'scheduler="DPM++ 2M SDE Karras"' \
  -i 'batch_size=1' \
  -i 'negative_prompt="unaestheticXL_Sky3.1, animal, cat, dog, big breasts"' \
  -i 'guidance_rescale=0.7'

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/charlesmccarthy/anima_pencil-xl@sha256:7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "vae": "sdxl-vae-fp16-fix",
      "seed": -1,
      "model": "Anima_Pencil-XL-v4.safetensors",
      "steps": 35,
      "width": 1184,
      "height": 864,
      "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
      "cfg_scale": 7,
      "scheduler": "DPM++ 2M SDE Karras",
      "batch_size": 1,
      "negative_prompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
      "guidance_rescale": 0.7
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-06-02T23:50:27.669548Z",
  "created_at": "2024-06-02T23:48:22.368000Z",
  "data_removed": false,
  "error": null,
  "id": "jacgrzn6w1rgp0cfvdd9ysk4nc",
  "input": {
    "vae": "sdxl-vae-fp16-fix",
    "seed": -1,
    "model": "Anima_Pencil-XL-v4.safetensors",
    "steps": 35,
    "width": 1184,
    "height": 864,
    "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
    "cfg_scale": 7,
    "scheduler": "DPM++ 2M SDE Karras",
    "batch_size": 1,
    "negative_prompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
    "guidance_rescale": 0.7
  },
  "logs": "0%|          | 0/35 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  3%|▎         | 1/35 [00:01<01:06,  1.96s/it]\n  6%|▌         | 2/35 [00:02<00:28,  1.15it/s]\n  9%|▊         | 3/35 [00:02<00:17,  1.79it/s]\n 11%|█▏        | 4/35 [00:02<00:12,  2.42it/s]\n 14%|█▍        | 5/35 [00:02<00:09,  3.01it/s]\n 17%|█▋        | 6/35 [00:02<00:08,  3.52it/s]\n 20%|██        | 7/35 [00:03<00:07,  3.95it/s]\n 23%|██▎       | 8/35 [00:03<00:06,  4.29it/s]\n 26%|██▌       | 9/35 [00:03<00:05,  4.55it/s]\n 29%|██▊       | 10/35 [00:03<00:05,  4.75it/s]\n 31%|███▏      | 11/35 [00:03<00:04,  4.89it/s]\n 34%|███▍      | 12/35 [00:03<00:04,  4.99it/s]\n 37%|███▋      | 13/35 [00:04<00:04,  5.06it/s]\n 40%|████      | 14/35 [00:04<00:04,  5.12it/s]\n 43%|████▎     | 15/35 [00:04<00:03,  5.16it/s]\n 46%|████▌     | 16/35 [00:04<00:03,  5.18it/s]\n 49%|████▊     | 17/35 [00:04<00:03,  5.20it/s]\n 51%|█████▏    | 18/35 [00:05<00:03,  5.21it/s]\n 54%|█████▍    | 19/35 [00:05<00:03,  5.22it/s]\n 57%|█████▋    | 20/35 [00:05<00:02,  5.23it/s]\n 60%|██████    | 21/35 [00:05<00:02,  5.23it/s]\n 63%|██████▎   | 22/35 [00:05<00:02,  5.23it/s]\n 66%|██████▌   | 23/35 [00:06<00:02,  5.23it/s]\n 69%|██████▊   | 24/35 [00:06<00:02,  5.23it/s]\n 71%|███████▏  | 25/35 [00:06<00:01,  5.23it/s]\n 74%|███████▍  | 26/35 [00:06<00:01,  5.23it/s]\n 77%|███████▋  | 27/35 [00:06<00:01,  5.23it/s]\n 80%|████████  | 28/35 [00:07<00:01,  5.23it/s]\n 83%|████████▎ | 29/35 [00:07<00:01,  5.23it/s]\n 86%|████████▌ | 30/35 [00:07<00:00,  5.23it/s]\n 89%|████████▊ | 31/35 [00:07<00:00,  5.23it/s]\n 91%|█████████▏| 32/35 [00:07<00:00,  5.23it/s]\n 94%|█████████▍| 33/35 [00:07<00:00,  5.23it/s]\n 97%|█████████▋| 34/35 [00:08<00:00,  5.23it/s]\n100%|██████████| 35/35 [00:08<00:00,  5.23it/s]\n100%|██████████| 35/35 [00:08<00:00,  4.19it/s]",
  "metrics": {
    "predict_time": 10.308153,
    "total_time": 125.301548
  },
  "output": [
    "https://replicate.delivery/pbxt/4lQPeySMkJV8dak0feO6NKDFGmZX1e1icJvOsWZOfYneQ3quE/0.png"
  ],
  "started_at": "2024-06-02T23:50:17.361395Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jacgrzn6w1rgp0cfvdd9ysk4nc",
    "cancel": "https://api.replicate.com/v1/predictions/jacgrzn6w1rgp0cfvdd9ysk4nc/cancel"
  },
  "version": "7e1d2d606d603ef3e4a4ecab1e7d1cf257efe2e5b3e5215a89f14c05113cceb3"
}

Generated in

10.3 seconds

Tweak it ShareReport

0%|          | 0/35 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,
  3%|▎         | 1/35 [00:01<01:06,  1.96s/it]
  6%|▌         | 2/35 [00:02<00:28,  1.15it/s]
  9%|▊         | 3/35 [00:02<00:17,  1.79it/s]
 11%|█▏        | 4/35 [00:02<00:12,  2.42it/s]
 14%|█▍        | 5/35 [00:02<00:09,  3.01it/s]
 17%|█▋        | 6/35 [00:02<00:08,  3.52it/s]
 20%|██        | 7/35 [00:03<00:07,  3.95it/s]
 23%|██▎       | 8/35 [00:03<00:06,  4.29it/s]
 26%|██▌       | 9/35 [00:03<00:05,  4.55it/s]
 29%|██▊       | 10/35 [00:03<00:05,  4.75it/s]
 31%|███▏      | 11/35 [00:03<00:04,  4.89it/s]
 34%|███▍      | 12/35 [00:03<00:04,  4.99it/s]
 37%|███▋      | 13/35 [00:04<00:04,  5.06it/s]
 40%|████      | 14/35 [00:04<00:04,  5.12it/s]
 43%|████▎     | 15/35 [00:04<00:03,  5.16it/s]
 46%|████▌     | 16/35 [00:04<00:03,  5.18it/s]
 49%|████▊     | 17/35 [00:04<00:03,  5.20it/s]
 51%|█████▏    | 18/35 [00:05<00:03,  5.21it/s]
 54%|█████▍    | 19/35 [00:05<00:03,  5.22it/s]
 57%|█████▋    | 20/35 [00:05<00:02,  5.23it/s]
 60%|██████    | 21/35 [00:05<00:02,  5.23it/s]
 63%|██████▎   | 22/35 [00:05<00:02,  5.23it/s]
 66%|██████▌   | 23/35 [00:06<00:02,  5.23it/s]
 69%|██████▊   | 24/35 [00:06<00:02,  5.23it/s]
 71%|███████▏  | 25/35 [00:06<00:01,  5.23it/s]
 74%|███████▍  | 26/35 [00:06<00:01,  5.23it/s]
 77%|███████▋  | 27/35 [00:06<00:01,  5.23it/s]
 80%|████████  | 28/35 [00:07<00:01,  5.23it/s]
 83%|████████▎ | 29/35 [00:07<00:01,  5.23it/s]
 86%|████████▌ | 30/35 [00:07<00:00,  5.23it/s]
 89%|████████▊ | 31/35 [00:07<00:00,  5.23it/s]
 91%|█████████▏| 32/35 [00:07<00:00,  5.23it/s]
 94%|█████████▍| 33/35 [00:07<00:00,  5.23it/s]
 97%|█████████▋| 34/35 [00:08<00:00,  5.23it/s]
100%|██████████| 35/35 [00:08<00:00,  5.23it/s]
100%|██████████| 35/35 [00:08<00:00,  4.19it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.032 to run on Replicate, or 31 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 34 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.