A restarted dual-stream inference approach with glyph priors and attention-guided masks improves occluded text rendering in pretrained diffusion models without fine-tuning.
TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.
T2I models frequently exhibit semantic errors, logical inconsistencies, and incorrect reasoning steps in visual text generation tasks, unlike text-only models.
citing papers explorer
-
Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending
A restarted dual-stream inference approach with glyph priors and attention-guided masks improves occluded text rendering in pretrained diffusion models without fine-tuning.
-
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.
-
Evaluating Reasoning Fidelity in Visual Text Generation
T2I models frequently exhibit semantic errors, logical inconsistencies, and incorrect reasoning steps in visual text generation tasks, unlike text-only models.