跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-07AI 評分39

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

AI 導讀

UltraText Bench 是一個評估圖像生成模型以提示詞生成密集視覺文字能力的中英雙語基準,涵蓋 432 個提示詞、24 類真實場景及三個難度級別。基準以 Q-Judger 評估文字保真度、清晰度、空間品質及場景品質;在所報設定下,Z-Image-Turbo 的清晰度比 Z-Image-Base 高 3.81 分,保真度則低 14.76 分。

正文

Published on Oct 7

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation must test sustained performance across more demanding scenes. We introduce UltraText Bench, a bilingual benchmark for prompt-only generation of dense visual text. It contains 432 prompts spanning 24 real-world scene categories and three difficulty levels, split equally between English and Chinese. Each human-reviewed prompt supplies exact strings for four to twelve text regions, paired with structured references for their content, placement, and visual attributes. We use the Q-Judger vision-language model to assess each image against the complete reference, reporting text fidelity, text clarity, spatial quality, and scene quality. Across 24 model configurations, these dimensions reveal different strengths: Z-Image-Turbo gains 3.81 clarity points over Z-Image-Base while losing 14.76 fidelity points under the reported settings. Performance also varies with workload; Qwen-Image-2512's English composite falls from 86.50 at L1 to 42.86 at L3. Ten participants took part in human evaluation of the automatic scores. Repository: https://github.com/LINs-lab/UltraText_Bench.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.09823

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.09823 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.09823 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.09823 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co