GLM-image

What it does

GLM-Image is a state-of-the-art open-source AI image generation model developed by Z.AI (Zhipu AI). Released under the Apache-2.0 license, it features a groundbreaking hybrid architecture combining a 9B-parameter autoregressive transformer with a 7B-parameter diffusion decoder. This architecture allows it to achieve industry-leading performance in precise text rendering (0.9116 CVTG-2K accuracy) and knowledge-intensive content generation, supporting high resolutions up to 2048×2048. The glm-image.top site operates as an independent service deploying and optimizing these open-source models.

Core features

• ✦Hybrid 9B Autoregressive + 7B Diffusion Architecture
• ✦Industry-leading Dense Text Rendering Excellence (0.9116 CVTG-2K accuracy)
• ✦Knowledge-Intensive Content Generation (for diagrams, posters, educational content)
• ✦Support for up to 2048×2048 resolution
• ✦Unified Text-to-Image (T2I) & Image-to-Image (I2I) capabilities

Use cases

• →Generating complex commercial posters and scientific diagrams requiring accurate information integration.
• →Creating photorealistic images with fine control over details, lighting, and textures.
• →Performing precise image transformations, editing, and style transfer (Image-to-Image).
• →Generating content requiring multi-subject and multi-style consistency.