MODEL REFERENCE / zai-org

zai-org/GLM-Image

Hybrid autoregressive + diffusion image generation model — text-to-image and image-to-image with strong text rendering and knowledge-intensive generation

9B AR generator + 7B DiT decoder, state-of-the-art text rendering in generated images

View on HuggingFace View on ModelScope

vLLMdense16B4,096 ctxvLLM 0.11.0+vLLM-Omninightlyomni

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Technical notes

Model notes and examples