# zai-org/GLM-Image

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

Repository: https://github.com/zai-org/GLM-Image
Canonical: https://ross.abutalabs.com/products/glm-image
Homepage: https://z.ai/blog/glm-image
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image2image, text2image
Last push: 2026-03-20T03:10:16+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 73, release rhythm 35, longevity 16
- inputs: {"age_days": 236, "days_push": 166, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1019, forks 93 (observed 2026-08-28T04:03:15.070942+00:00)

## What it is
GLM-Image is an open-source image generation model combining a 9B autoregressive generator with a 7B diffusion decoder, excelling at text rendering and knowledge-intensive image generation. It supports text-to-image and image-to-image tasks including editing, style transfer, and identity-preserving generation.

## Use cases
- generate images from text prompts
- render accurate text inside generated images
- edit images with natural language instructions
- style transfer on photos
- generate images with consistent subjects across multiple outputs
- create high-resolution detailed images from descriptions

## When to choose
- you need precise text rendering within generated images
- you need both text-to-image and image editing in one model
- knowledge-dense images like posters, infographics, or diagrams are your target
- you want high-fidelity 1K-2K resolution outputs

## When to avoid
- you only need lightweight or real-time image generation on consumer hardware
- you prefer mature latent diffusion ecosystems like Stable Diffusion with extensive tooling
- you cannot run 16B+ parameter models on GPU

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, image-processing, deep-learning, large-language-models
- platform: python
- tags: text-to-image, image-to-image, image-editing, text-rendering, diffusion, autoregressive, image-generation, huggingface, gpu, linux

## Member repositories
- zai-org/GLM-Image (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:15.070942+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:09:25.210568+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/GLM-Image (fetched 2026-08-28T04:03:15.070942+00:00, sha c62ab0ba90b1)
  - homepage: https://z.ai/blog/glm-image (fetched 2026-08-29T13:09:42.744358+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.