ZhipuAI's
GLM-Image
(16B, MIT) converted to
Core AI
for on-device image generation on Apple Silicon (macOS 27+) — the zoo's first
autoregressive + diffusion hybrid
.
GLM-Image generates in two stages: a
9B GLM-4 autoregressive model
writes the image as a
grid of discrete
visual prior tokens
(sampled left-to-right like an LLM, ~36 tok/s on
M4 Max), and a
7B flow-matching DiT
denoises the actual pixels conditioned on those
tokens, followed by a 16-channel VAE decode. Both native
1024×1024
and a faster
512×512
variant are included.
macOS only.
The AR (9.6 GB) + DiT (9.2 GB) weights are resolution-independent, so the
512 variant is no smaller — an iPhone port needs int4 + sequential component loading.
Components
Component
Description
Size
glm_image_ar.aimodelc
GLM-4-9B visual-token AR decoder (int8, S=1 decode, AOT h16c GPU)
Empty-glyph text embedding [1×1×1472] — the DiT text input for glyph-free prompts (no T5 needed at runtime)
6 KB
Weights are int8 (per-block-32) for AR/DiT; the VAE stays fp32 (fp16 overflows its
activations). Compute precision float16 on GPU. One resolution needs ~19.7 GB on disk
(AR + one DiT + one VAE).
Usage
Sample app (easiest)
CoreAIImageGen
(macOS)
— run the
CoreAIImageGenMac
scheme, pick
GLM-Image 1024 (AR+diffusion)
from the model
menu, tap
Download & Load
, type a prompt,
Generate
.
Steps 20
(default) ≈ 4.5 min/image on M4 Max — reference quality
Steps 12
≈ 2.5 min — nearly indistinguishable
The 512 variant generates in ~1 min
The AR stage is
sampled
(temperature 0.9 / top-p 0.75, the upstream
generation_config
),
so re-rolling the seed meaningfully changes composition.
Pipeline contract (build your own)
The hybrid does not fit Apple's high-level
CoreAIDiffusionPipeline
; the host loop is
~300 lines of Swift (see the app's
GlmImagePipeline
):
AR
:
tokenize(prompt) + fixed grid suffix
→ S=1 prefill/decode with host-computed
3D-mRoPE cos/sin → sample visual tokens → 2× upsample the large grid →
prior[1, N]
(N = 1024 @512, 4096 @1024).
DiT
: 20-step CFG (guidance 1.5,
prior_scale
1/0 for cond/uncond). Condition the
DiT on the
raw integer schedule
trunc(linspace(1000,1,steps+1)) − 1
; step the
latent with the
mu-shifted sigmas
σ' = μ/(μ + (1/σ − 1))
, μ = 0.75·side/256 + 0.25.
VAE
(fp32, CPU): latent → RGB.
⚠️ Feeding the DiT the
shifted
timesteps (sigma×1000) instead of the raw schedule skews
the adaLN time conditioning every step and drifts colors — resolution-dependently (mild
at 512, strong at 1024). This is the one non-obvious contract in the port.
Limitations
Glyph rendering (text in images) is not wired
: prompts containing quoted text
(
'…'
,
"…"
,
「…」
) route through a T5 glyph encoder that is not part of this bundle.
Keep prompts glyph-free.
Negative prompts are a no-op (GLM's CFG drops the prior tokens instead).
Image-to-image / editing (
GlmImageKVCache
) not yet exported.
Quality
Verified against the bf16 diffusers reference: DiT single-forward cosine 0.9999, VAE
byte-exact, AR prior-injection reproduces the reference composition; end-to-end output is
visually on par with
GlmImagePipeline
at the same step count.
GLM-Image-CoreAI huggingface.co is an AI model on huggingface.co that provides GLM-Image-CoreAI's model effect (), which can be used instantly with this mlboydaisuke GLM-Image-CoreAI model. huggingface.co supports a free trial of the GLM-Image-CoreAI model, and also provides paid use of the GLM-Image-CoreAI. Support call GLM-Image-CoreAI model through api, including Node.js, Python, http.
GLM-Image-CoreAI huggingface.co is an online trial and call api platform, which integrates GLM-Image-CoreAI's modeling effects, including api services, and provides a free online trial of GLM-Image-CoreAI, you can try GLM-Image-CoreAI online for free by clicking the link below.
mlboydaisuke GLM-Image-CoreAI online free url in huggingface.co:
GLM-Image-CoreAI is an open source model from GitHub that offers a free installation service, and any user can find GLM-Image-CoreAI on GitHub to install. At the same time, huggingface.co provides the effect of GLM-Image-CoreAI install, users can directly use GLM-Image-CoreAI installed effect in huggingface.co for debugging and trial. It also supports api for free installation.