thefluxtrain/oye-cartoon – Run with an API on Replicate

thefluxtrain / oye-cartoon

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Cold

Public
2.6K runs
A100 (80GB)
Weights
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a man cartoon character, sitting on a chair. brown pantsa man cartoon character, sitting on a chair. brown pants

Input prompt.

Default: "A girl cartoon character in a white background. She is looking right, and running."

image

*file

Preview

Input image

num_inference_steps

integer

(minimum: 1, maximum: 150)

Number of denoising steps

Default: 30

model

string

Control model to use.

Default: "oye-cartoon-v2"

crop_inpaint

boolean

Crop the image for inpainting

Default: false

Including guidance_scale and 14 more...

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

npx create-replicate --model=thefluxtrain/oye-cartoon

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 thefluxtrain/oye-cartoon using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "thefluxtrain/oye-cartoon:effccf7ca58124ea0b7ec7648f3d603c38a7c4434e3ffbeb14203ce264fa1223",
  {
    input: {
      lora: "saquiboye/oye-cartoon",
      image: "https://replicate.delivery/pbxt/MJa5EcWl474qATQBgPfKV1gQuz9UgxB2kXvUKUy11fefB96N/or.jpg",
      model: "oye-cartoon-v2",
      prompt: "a man cartoon character, sitting on a chair. brown pants",
      strength: 0.6,
      predictive: 0,
      weight_name: "pytorch_lora_weights.safetensors",
      crop_inpaint: false,
      guidance_scale: 7.5,
      image_strength: 1,
      position_delta: -16,
      num_inference_steps: 50
    }
  }
);
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 thefluxtrain/oye-cartoon using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "thefluxtrain/oye-cartoon:effccf7ca58124ea0b7ec7648f3d603c38a7c4434e3ffbeb14203ce264fa1223",
    input={
        "lora": "saquiboye/oye-cartoon",
        "image": "https://replicate.delivery/pbxt/MJa5EcWl474qATQBgPfKV1gQuz9UgxB2kXvUKUy11fefB96N/or.jpg",
        "model": "oye-cartoon-v2",
        "prompt": "a man cartoon character, sitting on a chair. brown pants",
        "strength": 0.6,
        "predictive": 0,
        "weight_name": "pytorch_lora_weights.safetensors",
        "crop_inpaint": False,
        "guidance_scale": 7.5,
        "image_strength": 1,
        "position_delta": -16,
        "num_inference_steps": 50
    }
)
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 thefluxtrain/oye-cartoon 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": "effccf7ca58124ea0b7ec7648f3d603c38a7c4434e3ffbeb14203ce264fa1223",
    "input": {
      "lora": "saquiboye/oye-cartoon",
      "image": "https://replicate.delivery/pbxt/MJa5EcWl474qATQBgPfKV1gQuz9UgxB2kXvUKUy11fefB96N/or.jpg",
      "model": "oye-cartoon-v2",
      "prompt": "a man cartoon character, sitting on a chair. brown pants",
      "strength": 0.6,
      "predictive": 0,
      "weight_name": "pytorch_lora_weights.safetensors",
      "crop_inpaint": false,
      "guidance_scale": 7.5,
      "image_strength": 1,
      "position_delta": -16,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-02-15T13:15:42.848025Z",
  "created_at": "2025-02-15T13:13:14.631000Z",
  "data_removed": false,
  "error": null,
  "id": "4fgjerq4gxrj00cn16ythgmnp0",
  "input": {
    "lora": "saquiboye/oye-cartoon",
    "image": "https://replicate.delivery/pbxt/MJa5EcWl474qATQBgPfKV1gQuz9UgxB2kXvUKUy11fefB96N/or.jpg",
    "model": "oye-cartoon-v2",
    "prompt": "a man cartoon character, sitting on a chair. brown pants",
    "strength": 0.6,
    "predictive": 0,
    "weight_name": "pytorch_lora_weights.safetensors",
    "guidance_scale": 7.5,
    "image_strength": 1,
    "position_delta": -16,
    "num_inference_steps": 50
  },
  "logs": "Not logged in!\nUsing control model: oye-cartoon-v2\nGenerating image with prompt: a man cartoon character, sitting on a chair. brown pants\nLogging in with token\nThe token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\nToken is valid (permission: fineGrained).\nYour token has been saved to /root/.cache/huggingface/token\nLogin successful\nUsing seed: 60414\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:01<00:59,  1.21s/it]\n  4%|▍         | 2/50 [00:02<00:53,  1.11s/it]\n  6%|▌         | 3/50 [00:03<00:53,  1.14s/it]\n  8%|▊         | 4/50 [00:04<00:52,  1.15s/it]\n 10%|█         | 5/50 [00:05<00:52,  1.16s/it]\n 12%|█▏        | 6/50 [00:06<00:51,  1.16s/it]\n 14%|█▍        | 7/50 [00:08<00:50,  1.17s/it]\n 16%|█▌        | 8/50 [00:09<00:49,  1.17s/it]\n 18%|█▊        | 9/50 [00:10<00:48,  1.17s/it]\n 20%|██        | 10/50 [00:11<00:46,  1.17s/it]\n 22%|██▏       | 11/50 [00:12<00:45,  1.18s/it]\n 24%|██▍       | 12/50 [00:13<00:44,  1.18s/it]\n 26%|██▌       | 13/50 [00:15<00:43,  1.18s/it]\n 28%|██▊       | 14/50 [00:16<00:42,  1.18s/it]\n 30%|███       | 15/50 [00:17<00:41,  1.18s/it]\n 32%|███▏      | 16/50 [00:18<00:40,  1.18s/it]\n 34%|███▍      | 17/50 [00:19<00:38,  1.18s/it]\n 36%|███▌      | 18/50 [00:21<00:37,  1.18s/it]\n 38%|███▊      | 19/50 [00:22<00:36,  1.18s/it]\n 40%|████      | 20/50 [00:23<00:35,  1.18s/it]\n 42%|████▏     | 21/50 [00:24<00:34,  1.18s/it]\n 44%|████▍     | 22/50 [00:25<00:33,  1.18s/it]\n 46%|████▌     | 23/50 [00:26<00:31,  1.18s/it]\n 48%|████▊     | 24/50 [00:28<00:30,  1.18s/it]\n 50%|█████     | 25/50 [00:29<00:29,  1.18s/it]\n 52%|█████▏    | 26/50 [00:30<00:28,  1.18s/it]\n 54%|█████▍    | 27/50 [00:31<00:27,  1.18s/it]\n 56%|█████▌    | 28/50 [00:32<00:25,  1.18s/it]\n 58%|█████▊    | 29/50 [00:34<00:24,  1.18s/it]\n 60%|██████    | 30/50 [00:35<00:23,  1.18s/it]\n 62%|██████▏   | 31/50 [00:36<00:22,  1.18s/it]\n 64%|██████▍   | 32/50 [00:37<00:21,  1.18s/it]\n 66%|██████▌   | 33/50 [00:38<00:20,  1.18s/it]\n 68%|██████▊   | 34/50 [00:39<00:18,  1.18s/it]\n 70%|███████   | 35/50 [00:41<00:17,  1.18s/it]\n 72%|███████▏  | 36/50 [00:42<00:16,  1.18s/it]\n 74%|███████▍  | 37/50 [00:43<00:15,  1.18s/it]\n 76%|███████▌  | 38/50 [00:44<00:14,  1.18s/it]\n 78%|███████▊  | 39/50 [00:45<00:12,  1.18s/it]\n 80%|████████  | 40/50 [00:47<00:11,  1.18s/it]\n 82%|████████▏ | 41/50 [00:48<00:10,  1.18s/it]\n 84%|████████▍ | 42/50 [00:49<00:09,  1.18s/it]\n 86%|████████▌ | 43/50 [00:50<00:08,  1.18s/it]\n 88%|████████▊ | 44/50 [00:51<00:07,  1.18s/it]\n 90%|█████████ | 45/50 [00:52<00:05,  1.18s/it]\n 92%|█████████▏| 46/50 [00:54<00:04,  1.18s/it]\n 94%|█████████▍| 47/50 [00:55<00:03,  1.18s/it]\n 96%|█████████▌| 48/50 [00:56<00:02,  1.18s/it]\n 98%|█████████▊| 49/50 [00:57<00:01,  1.18s/it]\n100%|██████████| 50/50 [00:58<00:00,  1.18s/it]\n100%|██████████| 50/50 [00:58<00:00,  1.18s/it]",
  "metrics": {
    "predict_time": 67.027413859,
    "total_time": 148.217025
  },
  "output": "https://replicate.delivery/yhqm/5SPtvl2AEY6aEJgrPaKI46fv3WsjBNj9lEdH4uVpiLGfVkPUA/out.png",
  "started_at": "2025-02-15T13:14:35.820611Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-sbd5o3coxryhuuknebqvdg6c34nhrgc76uofqa2uc7qigrxwdzvq",
    "get": "https://api.replicate.com/v1/predictions/4fgjerq4gxrj00cn16ythgmnp0",
    "cancel": "https://api.replicate.com/v1/predictions/4fgjerq4gxrj00cn16ythgmnp0/cancel"
  },
  "version": "a4862b811bb3af0baf99cff192e2649bda525b441696d02fb80f40ce52290652"
}

Generated in

67.0 seconds

Tweak it ShareReport

Not logged in!
Using control model: oye-cartoon-v2
Generating image with prompt: a man cartoon character, sitting on a chair. brown pants
Logging in with token
The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: fineGrained).
Your token has been saved to /root/.cache/huggingface/token
Login successful
Using seed: 60414
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<00:59,  1.21s/it]
  4%|▍         | 2/50 [00:02<00:53,  1.11s/it]
  6%|▌         | 3/50 [00:03<00:53,  1.14s/it]
  8%|▊         | 4/50 [00:04<00:52,  1.15s/it]
 10%|█         | 5/50 [00:05<00:52,  1.16s/it]
 12%|█▏        | 6/50 [00:06<00:51,  1.16s/it]
 14%|█▍        | 7/50 [00:08<00:50,  1.17s/it]
 16%|█▌        | 8/50 [00:09<00:49,  1.17s/it]
 18%|█▊        | 9/50 [00:10<00:48,  1.17s/it]
 20%|██        | 10/50 [00:11<00:46,  1.17s/it]
 22%|██▏       | 11/50 [00:12<00:45,  1.18s/it]
 24%|██▍       | 12/50 [00:13<00:44,  1.18s/it]
 26%|██▌       | 13/50 [00:15<00:43,  1.18s/it]
 28%|██▊       | 14/50 [00:16<00:42,  1.18s/it]
 30%|███       | 15/50 [00:17<00:41,  1.18s/it]
 32%|███▏      | 16/50 [00:18<00:40,  1.18s/it]
 34%|███▍      | 17/50 [00:19<00:38,  1.18s/it]
 36%|███▌      | 18/50 [00:21<00:37,  1.18s/it]
 38%|███▊      | 19/50 [00:22<00:36,  1.18s/it]
 40%|████      | 20/50 [00:23<00:35,  1.18s/it]
 42%|████▏     | 21/50 [00:24<00:34,  1.18s/it]
 44%|████▍     | 22/50 [00:25<00:33,  1.18s/it]
 46%|████▌     | 23/50 [00:26<00:31,  1.18s/it]
 48%|████▊     | 24/50 [00:28<00:30,  1.18s/it]
 50%|█████     | 25/50 [00:29<00:29,  1.18s/it]
 52%|█████▏    | 26/50 [00:30<00:28,  1.18s/it]
 54%|█████▍    | 27/50 [00:31<00:27,  1.18s/it]
 56%|█████▌    | 28/50 [00:32<00:25,  1.18s/it]
 58%|█████▊    | 29/50 [00:34<00:24,  1.18s/it]
 60%|██████    | 30/50 [00:35<00:23,  1.18s/it]
 62%|██████▏   | 31/50 [00:36<00:22,  1.18s/it]
 64%|██████▍   | 32/50 [00:37<00:21,  1.18s/it]
 66%|██████▌   | 33/50 [00:38<00:20,  1.18s/it]
 68%|██████▊   | 34/50 [00:39<00:18,  1.18s/it]
 70%|███████   | 35/50 [00:41<00:17,  1.18s/it]
 72%|███████▏  | 36/50 [00:42<00:16,  1.18s/it]
 74%|███████▍  | 37/50 [00:43<00:15,  1.18s/it]
 76%|███████▌  | 38/50 [00:44<00:14,  1.18s/it]
 78%|███████▊  | 39/50 [00:45<00:12,  1.18s/it]
 80%|████████  | 40/50 [00:47<00:11,  1.18s/it]
 82%|████████▏ | 41/50 [00:48<00:10,  1.18s/it]
 84%|████████▍ | 42/50 [00:49<00:09,  1.18s/it]
 86%|████████▌ | 43/50 [00:50<00:08,  1.18s/it]
 88%|████████▊ | 44/50 [00:51<00:07,  1.18s/it]
 90%|█████████ | 45/50 [00:52<00:05,  1.18s/it]
 92%|█████████▏| 46/50 [00:54<00:04,  1.18s/it]
 94%|█████████▍| 47/50 [00:55<00:03,  1.18s/it]
 96%|█████████▌| 48/50 [00:56<00:02,  1.18s/it]
 98%|█████████▊| 49/50 [00:57<00:01,  1.18s/it]
100%|██████████| 50/50 [00:58<00:00,  1.18s/it]
100%|██████████| 50/50 [00:58<00:00,  1.18s/it]

This example was created by a different version, thefluxtrain/oye-cartoon:a4862b81.

Examples

View more examples

Run time and cost

This model costs approximately $0.22 to run on Replicate, or 4 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 3 minutes. The predict time for this model varies significantly based on the inputs.

Readme

License subjected to Flux 1 dev license by Black forest lab - https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev

Try it on Replicate - https://replicate.com/thefluxtrain/oye-cartoon

or on TheFluxTrain - (link to be added soon)

Example- Input image- image/jpeg

Prompt - photo of a man cartoon character in a white background. He is looking right, and running. Brown pants Output -

image/png

More output-

image/png