GLM-Image
Z.aiGLM-Image is Z.ai's open image generation model, released in January 2026. A 9B autoregressive generator built from GLM-4-9B lays out the image as visual tokens and a 7B diffusion decoder renders them, which makes it strong at legible text inside images and at knowledge-heavy prompts such as posters and diagrams. The same model edits images, transfers styles and keeps subjects consistent across images.
The weights are MIT-licensed and the repository code Apache 2.0; the vision tokenizer and encoder weights it carries come from X-Omni under Apache 2.0. Z.ai also serves GLM-Image through its API. CogView, Z.ai's earlier image line, is not part of this entry.
Openness
3 high confidence- weights
- open (the GLM-Image checkpoint downloads from the Hub without a gate)
- data
- closed (the README describes the training stages, but no training data is released or itemized)
- code
- partial (inference code and a LoRA fine-tuning script; the pretraining code is not published)
- license
- MIT (the GLM-Image weights)+Apache-2.0 (the repository code, and the X-Omni vision tokenizer and encoder weights the model incorporates)
GLM-Image's weights are MIT-licensed and the code is Apache 2.0, so the model can be used and modified freely. Only inference and LoRA fine-tuning code is published, not the pretraining pipeline, and the training data is not released.
- https://huggingface.co/api/models/zai-org/GLM-Image?expand[]=downloads&expand[]=likes&expand[]=cardData&expand[]=gated&expand[]=lastModified&expand[]=createdAt&expand[]=siblings recorded 2026-11-12
Hugging Face API record for zai-org/GLM-Image: license mit, gated false; transformer, VAE, text-encoder and vision-language-encoder safetensors.
- https://huggingface.co/zai-org/GLM-Image/raw/main/README.md recorded 2026-11-12
Model card: "license: mit"; "The overall GLM-Image model is released under the MIT License"; "This project incorporates the VQ tokenizer weights and VIT weights from X-Omni/X-Omni-En, which are licensed under the Apache License, Version 2.0."
- https://raw.githubusercontent.com/zai-org/GLM-Image/main/LICENSE recorded 2026-11-12
Repository LICENSE body: Apache License, Version 2.0.
- https://raw.githubusercontent.com/zai-org/GLM-Image/main/README.md recorded 2026-11-12
README: "Autoregressive generator: a 9B-parameter model initialized from GLM-4-9B-0414"; "Diffusion Decoder: a 7B-parameter decoder"; post-training "with decoupled reinforcement learning" using GRPO; no training dataset is named or linked.
- https://ungh.cc/repos/zai-org/GLM-Image/files/main recorded 2026-11-12
Repository file list: README, examples and a finetune/ directory with finetune_lora.py; no pretraining pipeline.
Adoption
2 high confidenceAdoption is measured as Hugging Face downloads of the single GLM-Image checkpoint. Use through Z.ai's API is not counted.
- https://huggingface.co/api/models?author=zai-org&search=GLM-Image&sort=downloads&direction=-1&limit=100 recorded 2026-11-12
Listing: zai-org/GLM-Image, 12284 downloads, the only GLM-Image repository.
Capability
2 medium confidenceGLM-Image places in the lower half of the public image arena, below FLUX.2 [dev]. Its strengths, text rendering and knowledge-heavy layouts, are a narrower slice than the arena's general prompts.
- https://artificialanalysis.ai/image/leaderboard/text-to-image recorded 2026-11-12
Overall board (112 models): "GLM-Image" 93rd, Elo 893, from Z AI, with an open-weights link to zai-org/GLM-Image.
Verified 2026-11-12