image generation
GLM-Image
Z.ai image generation model with a hybrid autoregressive and diffusion design, strong at text rendering and knowledge-intensive generation, and also supporting image editing.
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
ReleasedJan 2026
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Benchmark Results
independent
Artificial Analysis Text-to-Image Arena AA-Image-T2I v2.0generative media
independent
891 +-7; 95% interval 884 to 898
5009001,300
Score in Elo; the axis starts at 500, as Elo has no zero. Higher is better.
rank 107, AA Text-to-Image leaderboard, overall
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
continued pretrain
GLM-4-9B-0414 is the parent (continued pretrain)high confidencemodel cardWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Runtimes
Identity
- Developer
- Z.ai (Zhipu)
- Family
- GLM
- Released
- Jan 2026 sourcessecondary report
- Weights published
- –
- Record checked
- 11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- hybrid Autoregressive generator (9B, initialized from GLM-4-9B-0414) plus a 7B single-stream DiT diffusion decoder
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 9B autoregressive generator plus 7B diffusion decoder
- Context length
- not in the notes
- Input
- text, image
- Output
- image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- VQ tokenizer and ViT weights from X-Omni remain under Apache 2.0
- Runtimes
- SGLang
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperZ.ai (Zhipu)company, China
Z.ai (Zhipu)company, ChinaModelGLM-ImageZ.ai (Zhipu), image generation
GLM-ImageZ.ai (Zhipu), image generationUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- huggingface.co/zai-org/GLM-Image https://huggingface.co/zai-org/GLM-Image
- artificialanalysis.ai/image/leaderboard/text-to-image https://artificialanalysis.ai/image/leaderboard/text-to-image
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GLM-Image", https://aurion.semai.id/models/zhipu-zai-glm-image/, records of October 2026.