GLM-Image released GLM-Image is a new open-source, industrial-grade image generation model that blends auto-regressive semantic modeling with a diffusion decoder to deliver high-fidelity visuals and industry-leading text rendering. This is the first open-source, industrial-grade autoregressive image generation model, and it absolutely dominates text rendering benchmarks. GLM-Image tops the CVTG-2K text rendering leaderboard with 91.16% word accuracy – beating even closed-source giants like GPT Image 1 and Seedream 4.5. For Chinese text rendering on LongText-Bench, it scores an impressive 97.88%, crushing GPT Image 1's measly 61.9%.