asiryan/anima-pencil-xl-v5 – Run with an API on Replicate

asiryan / anima-pencil-xl-v5

Anima Pencil XL v5 Model (Text2Img, Img2Img and Inpainting)

Cold

Public
16.4K runs
A100 (80GB)
GitHub
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality

Input prompt

Default: "1boy, solo, black hair, black skin, blue sky, cape, colored skin, from side, full moon, looking at another, moon, mountainous horizon, night, outdoors, scenery, sky, standing, white cape, wide shot, yellow theme"

negative_prompt

string

Shift + Return to add a new line

photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eyephoto, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye

Negative Input prompt

Default: "photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye"

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: 7

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/anima-pencil-xl-v5

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/anima-pencil-xl-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "asiryan/anima-pencil-xl-v5:40461ea31f38c0c935e763fd263343c294a4c7ac89e0d6ec6e94433ec9e81693",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality",
      strength: 0.8,
      scheduler: "K_EULER_ANCESTRAL",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7,
      negative_prompt: "photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye",
      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/anima-pencil-xl-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "asiryan/anima-pencil-xl-v5:40461ea31f38c0c935e763fd263343c294a4c7ac89e0d6ec6e94433ec9e81693",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality",
        "strength": 0.8,
        "scheduler": "K_EULER_ANCESTRAL",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7,
        "negative_prompt": "photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye",
        "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/anima-pencil-xl-v5 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/anima-pencil-xl-v5:40461ea31f38c0c935e763fd263343c294a4c7ac89e0d6ec6e94433ec9e81693",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality",
      "strength": 0.8,
      "scheduler": "K_EULER_ANCESTRAL",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7,
      "negative_prompt": "photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye",
      "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": "2024-11-26T19:53:31.862633Z",
  "created_at": "2024-11-26T19:53:26.794000Z",
  "data_removed": false,
  "error": null,
  "id": "eahtaz9e19rj00ckd84sxe31n8",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality",
    "strength": 0.8,
    "scheduler": "K_EULER_ANCESTRAL",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7,
    "negative_prompt": "photo, 3d, realistic, disfigured, kitsch, ugly, oversaturated, grain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye",
    "num_inference_steps": 40
  },
  "logs": "Using seed: 23549\nPrompt: 1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality\ntxt2img mode\nToken indices sequence length is longer than the specified maximum sequence length for this model (78 > 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: ['quality']\nToken indices sequence length is longer than the specified maximum sequence length for this model (78 > 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: ['quality']\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:04,  8.90it/s]\n  5%|▌         | 2/40 [00:00<00:04,  8.88it/s]\n  8%|▊         | 3/40 [00:00<00:04,  8.88it/s]\n 10%|█         | 4/40 [00:00<00:04,  8.88it/s]\n 12%|█▎        | 5/40 [00:00<00:03,  8.88it/s]\n 15%|█▌        | 6/40 [00:00<00:03,  8.88it/s]\n 18%|█▊        | 7/40 [00:00<00:03,  8.86it/s]\n 20%|██        | 8/40 [00:00<00:03,  8.85it/s]\n 22%|██▎       | 9/40 [00:01<00:03,  8.84it/s]\n 25%|██▌       | 10/40 [00:01<00:03,  8.84it/s]\n 28%|██▊       | 11/40 [00:01<00:03,  8.83it/s]\n 30%|███       | 12/40 [00:01<00:03,  8.83it/s]\n 32%|███▎      | 13/40 [00:01<00:03,  8.83it/s]\n 35%|███▌      | 14/40 [00:01<00:02,  8.83it/s]\n 38%|███▊      | 15/40 [00:01<00:02,  8.84it/s]\n 40%|████      | 16/40 [00:01<00:02,  8.84it/s]\n 42%|████▎     | 17/40 [00:01<00:02,  8.84it/s]\n 45%|████▌     | 18/40 [00:02<00:02,  8.84it/s]\n 48%|████▊     | 19/40 [00:02<00:02,  8.83it/s]\n 50%|█████     | 20/40 [00:02<00:02,  8.83it/s]\n 52%|█████▎    | 21/40 [00:02<00:02,  8.84it/s]\n 55%|█████▌    | 22/40 [00:02<00:02,  8.84it/s]\n 57%|█████▊    | 23/40 [00:02<00:01,  8.85it/s]\n 60%|██████    | 24/40 [00:02<00:01,  8.84it/s]\n 62%|██████▎   | 25/40 [00:02<00:01,  8.85it/s]\n 65%|██████▌   | 26/40 [00:02<00:01,  8.84it/s]\n 68%|██████▊   | 27/40 [00:03<00:01,  8.84it/s]\n 70%|███████   | 28/40 [00:03<00:01,  8.84it/s]\n 72%|███████▎  | 29/40 [00:03<00:01,  8.83it/s]\n 75%|███████▌  | 30/40 [00:03<00:01,  8.83it/s]\n 78%|███████▊  | 31/40 [00:03<00:01,  8.82it/s]\n 80%|████████  | 32/40 [00:03<00:00,  8.82it/s]\n 82%|████████▎ | 33/40 [00:03<00:00,  8.82it/s]\n 85%|████████▌ | 34/40 [00:03<00:00,  8.83it/s]\n 88%|████████▊ | 35/40 [00:03<00:00,  8.83it/s]\n 90%|█████████ | 36/40 [00:04<00:00,  8.82it/s]\n 92%|█████████▎| 37/40 [00:04<00:00,  8.83it/s]\n 95%|█████████▌| 38/40 [00:04<00:00,  8.83it/s]\n 98%|█████████▊| 39/40 [00:04<00:00,  8.83it/s]\n100%|██████████| 40/40 [00:04<00:00,  8.83it/s]\n100%|██████████| 40/40 [00:04<00:00,  8.84it/s]",
  "metrics": {
    "predict_time": 5.059142961,
    "total_time": 5.068633
  },
  "output": [
    "https://replicate.delivery/yhqm/qKd8gDeeqtufeQImZV1ECZgbwjwP1vSHrNcv89KSTf0YnsneE/out-0.png"
  ],
  "started_at": "2024-11-26T19:53:26.803490Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-2hjtpiqj7rawzeqeje5h5cwytfamdr2vajbohjiyxnsd6ahrxy4a",
    "get": "https://api.replicate.com/v1/predictions/eahtaz9e19rj00ckd84sxe31n8",
    "cancel": "https://api.replicate.com/v1/predictions/eahtaz9e19rj00ckd84sxe31n8/cancel"
  },
  "version": "a7e6283a79ec6144833fe5543915b631c8f2c328216665da17831d169039f447"
}

Generated in

5.1 seconds

Tweak it ShareReport

Using seed: 23549
Prompt: 1girl, solo, ahoge, blue eyes, brown footwear, brown mittens, cardigan, fur trim, fur-trimmed sleeves, green scarf, hand up, long hair, looking at viewer, mittens, one eye closed, orange background, orange hair, scarf, shoes, sitting, striped clothes, striped scarf, wavy hair, yellow cardigan, masterpiece, best quality
txt2img mode
Token indices sequence length is longer than the specified maximum sequence length for this model (78 > 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: ['quality']
Token indices sequence length is longer than the specified maximum sequence length for this model (78 > 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: ['quality']
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:04,  8.90it/s]
  5%|▌         | 2/40 [00:00<00:04,  8.88it/s]
  8%|▊         | 3/40 [00:00<00:04,  8.88it/s]
 10%|█         | 4/40 [00:00<00:04,  8.88it/s]
 12%|█▎        | 5/40 [00:00<00:03,  8.88it/s]
 15%|█▌        | 6/40 [00:00<00:03,  8.88it/s]
 18%|█▊        | 7/40 [00:00<00:03,  8.86it/s]
 20%|██        | 8/40 [00:00<00:03,  8.85it/s]
 22%|██▎       | 9/40 [00:01<00:03,  8.84it/s]
 25%|██▌       | 10/40 [00:01<00:03,  8.84it/s]
 28%|██▊       | 11/40 [00:01<00:03,  8.83it/s]
 30%|███       | 12/40 [00:01<00:03,  8.83it/s]
 32%|███▎      | 13/40 [00:01<00:03,  8.83it/s]
 35%|███▌      | 14/40 [00:01<00:02,  8.83it/s]
 38%|███▊      | 15/40 [00:01<00:02,  8.84it/s]
 40%|████      | 16/40 [00:01<00:02,  8.84it/s]
 42%|████▎     | 17/40 [00:01<00:02,  8.84it/s]
 45%|████▌     | 18/40 [00:02<00:02,  8.84it/s]
 48%|████▊     | 19/40 [00:02<00:02,  8.83it/s]
 50%|█████     | 20/40 [00:02<00:02,  8.83it/s]
 52%|█████▎    | 21/40 [00:02<00:02,  8.84it/s]
 55%|█████▌    | 22/40 [00:02<00:02,  8.84it/s]
 57%|█████▊    | 23/40 [00:02<00:01,  8.85it/s]
 60%|██████    | 24/40 [00:02<00:01,  8.84it/s]
 62%|██████▎   | 25/40 [00:02<00:01,  8.85it/s]
 65%|██████▌   | 26/40 [00:02<00:01,  8.84it/s]
 68%|██████▊   | 27/40 [00:03<00:01,  8.84it/s]
 70%|███████   | 28/40 [00:03<00:01,  8.84it/s]
 72%|███████▎  | 29/40 [00:03<00:01,  8.83it/s]
 75%|███████▌  | 30/40 [00:03<00:01,  8.83it/s]
 78%|███████▊  | 31/40 [00:03<00:01,  8.82it/s]
 80%|████████  | 32/40 [00:03<00:00,  8.82it/s]
 82%|████████▎ | 33/40 [00:03<00:00,  8.82it/s]
 85%|████████▌ | 34/40 [00:03<00:00,  8.83it/s]
 88%|████████▊ | 35/40 [00:03<00:00,  8.83it/s]
 90%|█████████ | 36/40 [00:04<00:00,  8.82it/s]
 92%|█████████▎| 37/40 [00:04<00:00,  8.83it/s]
 95%|█████████▌| 38/40 [00:04<00:00,  8.83it/s]
 98%|█████████▊| 39/40 [00:04<00:00,  8.83it/s]
100%|██████████| 40/40 [00:04<00:00,  8.83it/s]
100%|██████████| 40/40 [00:04<00:00,  8.84it/s]

This output was created using a different version of the model, asiryan/anima-pencil-xl-v5:a7e6283a.

Examples

View more examples

Run time and cost

This model costs approximately $0.0078 to run on Replicate, or 128 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 6 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Anima Pencil XL v5 Model (Text2Img, Img2Img and Inpainting)