Instructions to use zai-org/GLM-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/GLM-Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zai-org/GLM-Image", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
I cannot generate anti-aesthetics images
#9
by weathon - opened
prompt: The lighthouse tower melts like wax, flowing into spiral waves of a violet ocean. Buildings warp into non-Euclidean angles where gravity vanishes, and the sky features floating eyes in place of clouds. Distorted landscapes and psychedelic colors bleed into a dreamlike hallway, creating an uncanny, hallucinatory scene where stone surfaces behave like liquid glass.
Also tried Chinese version: 空荡荡的游乐场里孤零零地挂着一个秋千,但画面严重失焦;边缘模糊不清,画面中充斥着颗粒感的噪点,秋千的链条也略微扭曲变形。模糊不清的影像让游乐场显得诡异而孤寂,仿佛一个被恐惧和悲伤遗弃的地方。
In comparsion, GPT can do it:
Is this intended?
small language text encoder =)


