What is GLM-Image?

GLM-Image is a state-of-the-art open-source image generation model developed by Z.AI (also known as Zhipu AI), released on January 14, 2026. It features a groundbreaking hybrid architecture combining a 9B-parameter autoregressive transformer with a 7B-parameter diffusion decoder. The model achieves industry-leading performance in text rendering (0.9116 CVTG-2K accuracy) and knowledge-intensive content generation. glm-image.top is an independent AI service that deploys and optimizes Apache-2.0 licensed models on its own infrastructure.

How to use GLM-Image?

Users can access GLM-Image through the glm-image.top platform. The service offers credit-based pricing where credits are usage units consumed per task. Users can purchase credit packs (Starter, Monthly, or Yearly plans) and then generate images by entering text prompts or providing input images for image-to-image editing. The platform supports resolutions up to 2048×2048 with custom sizes from 512px to 2048px.

Core features of GLM-Image

Text-to-Image Generation: Generate high-fidelity images from text prompts with exceptional prompt adherence
Image-to-Image Editing: Precise image transformations including editing, style transfer, and identity preservation
Dense Text Rendering: Industry-leading accuracy for multi-line, multi-region text with 0.9116 CVTG-2K score
Knowledge Integration: Embeds logical structures and accurate information for educational content, posters, and diagrams
Multi-Subject Consistency: Maintains identity and style consistency across multiple subjects
High Resolution Support: Supports resolutions up to 2048×2048 natively
Bilingual Text Rendering: Supports text rendering in multiple languages
Instruction Following: Fine-grained control over image elements with structured reasoning chain