← 研踪 PaperTrailarXiv:2611.12042 · v1
Four-Step Text-Bearing Image Generation via Distillation with Local Response Regularization and Teacher-Guided Training
首次提交 2026-11-09 16:20
版本更新 2026-11-09 16:20
雷达观测 2026-11-10 13:18
摘要
Generating text-bearing images requires coherent scenes and accurate characters. Large text-to-image models improve both capabilities through repeated denoising, at substantial sampling cost. Few-step distillation reduces this cost but requires the student to organize scenes and refine glyphs within a short trajectory. We present a four-step distillation framework combining local response regularization with teacher-guided text training. Built on distribution matching, the framework distills the GLM-Image DiT while retaining its autoregressive visual prior, glyph encoder, and VAE. A path-length penalty promotes consistent local responses of the conditional denoising field. Progressive training combines synthetic strings with teacher-generated imagery to preserve character accuracy and scene-integrated typography. The student achieves GenEval Overall 0.84 and CVTG-2K word accuracy 0.5045, compared with 0.81 and 0.1690 for four-step TDM. A coefficient study favors , and Qwen-Image experiments show additional gains from response regularization and text supervision. Single-image inference takes 1.742 s, compared with 5.818 s for the teacher, yielding a speedup at the same 40 GB GPU memory requirement.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 16:20 · 最新观测版本
Four-Step Text-Bearing Image Generation via Distillation with Local Response Regularization and Teacher-Guided Training
Generating text-bearing images requires coherent scenes and accurate characters. Large text-to-image models improve both capabilities through repeated denoising, at substantial sampling cost. Few-step distillation reduces this cost but requires the student to organize scenes and refine glyphs within a short trajectory. We present a four-step distillation framework combining local response regularization with teacher-guided text training. Built on distribution matching, the framework distills the GLM-Image DiT while retaining its autoregressive visual prior, glyph encoder, and VAE. A path-length penalty promotes consistent local responses of the conditional denoising field. Progressive training combines synthetic strings with teacher-generated imagery to preserve character accuracy and scene-integrated typography. The student achieves GenEval Overall 0.84 and CVTG-2K word accuracy 0.5045, compared with 0.81 and 0.1690 for four-step TDM. A coefficient study favors , and Qwen-Image experiments show additional gains from response regularization and text supervision. Single-image inference takes 1.742 s, compared with 5.818 s for the teacher, yielding a speedup at the same 40 GB GPU memory requirement.
查看此版本解读 →查看此版本原文 ↗