HERIUN/vqfont-korean-handwriting

image-to-image model by HERIUN

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Few-shot Korean glyph generation. Give it a handful of glyph images in one style (a font or someone's handwriting) and any Hangul text; it draws every character of that text in that style. This is VQ-Font (AAAI 2024) retrained for Hangul, packaged for inference only (no training code, runs on CPU). 한국어 요약: 손글씨/폰트 글자 이미지 몇 장(라벨 없어도 됨)으로 임의의 한글을 같은 스타일로 생성하는 VQ-Font 한글 재학습 모델입니다. 학습 밖 폰트 재현은 DM-Font·MX-Font++ 보다 좋고, 스캔한 실제 손글씨에서는 학습 폰트 쪽으로 정돈되는 경향이 있습니다. Requirements: torch, numpy, pillow, safetensors, huggingfacehub. Reference images. One glyph per image, dark ink on a light background. They are cropped to the ink and centered like the training renders (fitrefs=False disables this). 5–10 references are enough; labels are optional. How references are chosen. Each output character is conditioned on 3 references: characters) are all given, they are used. This is the setting the model…

HERIUN/vqfont-korean-handwriting on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-29T08:10:46.532Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

HERIUN/vqfont-korean-handwriting is a image-to-image model repository published by HERIUN on Hugging Face. The source reports the pytorch library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: image-to-image
Library: pytorch
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 16,670,721
Architecture: Not reported
License: other
Access: Not gated by Hugging Face
Created: 2026-10-29T06:44:30.000Z
Last modified: 2026-10-29T06:45:38.000Z

Compatibility and lineage

Reported languages: ko

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion