[ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering""
In version 1, a reference image is used as the background through a visual encoder. By providing bbox information and a text prompt, text is generated on that image background. Is this feature not supported in version 2?
code link v2
In version 1, a reference image is used as the background through a visual encoder. By providing bbox information and a text prompt, text is generated on that image background. Is this feature not supported in version 2? code link v2