Model reference · open weights

manga-ocr-2025-onnx

Available as managed deployment LLMs l0wgear · community Image→text 1 variants 2k dl/mo

manga-ocr-2025-onnx is an open-weight language model from l0wgear. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byl0wgear
TypeLanguage models
TaskImage→text
Released2025-06-28
Popularity2k downloads / month
LicenceUnknown

About

What manga-ocr-2025-onnx is

This is an ONNX version of the Manga OCR model, designed for optical character recognition of Japanese text, with a primary focus on manga.

This model is based on the original work by kha-white/manga-ocr, kha-white/manga-ocr-base and modification by jzhang533/manga-ocr-base-2025. The models in this repository were exported to the ONNX format using Hugging Face Optimum.

Read the full model card

Original Model Information

Manga OCR utilizes the Vision Encoder Decoder framework. It is designed to be a high-quality text recognition tool, robust against various scenarios specific to manga:

  • Both vertical and horizontal text
  • Text with furigana
  • Text overlaid on images
  • A wide variety of fonts and font styles
  • Low-quality images

The original training data included manga109-s and synthetic data.

Using the ONNX Models

To use these ONNX models for inference, you will need the optimum library. You can install it as follows:

pip install optimum[onnxruntime]

Here is an example of how to run inference with the ONNX models:

from transformers import TrOCRProcessor
from optimum.onnxruntime import ORTModelForVision2Seq
from PIL import Image

# Load the processor and model
processor = TrOCRProcessor.from_pretrained("l0wgear/manga-ocr-2025-onnx")
model = ORTModelForVision2Seq.from_pretrained("l0wgear/manga-ocr-2025-onnx")

# Load an image
image = Image.open("path/to/your/manga/image.jpg").convert("RGB")

# Process the image and generate text
pixel_values = processor(images=image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(generated_text)

Acknowledgements

  • Original Author: kha-white for creating the original Manga OCR.
  • Fine-tuning: jzhang533 for training the manga-ocr-base-2025 model.

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys manga-ocr-2025-onnx for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (manga-ocr-2025-onnx below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"manga-ocr-2025-onnx","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms