GLM-Image for ComfyUI
A lot of you have been curious about the new GLM-Image model. It is a single model that can generate new images and edit existing ones in the same pipeline. No separate text-to-image and image-to-image models. Just one unified system.
The full GLM-Image model is very large and will take time before lighter versions run comfortably on hobby GPUs. This release gives you something to experiment with right now.
This 4-bit SDNQ build runs on a 24GB GPU. It is slower and not yet top tier in quality, but it provides a real taste of the new autoregressive approach and lets you explore the workflow today.
GLM-Image Generator 4-bit SDNQ
A local text-to-image and image-to-image generator powered by GLM-Image, an autoregressive diffusion model designed for strong prompt understanding and precise visual control.
Why GLM-Image
- Unified pipeline for generation and editing
- Autoregressive planning before diffusion rendering
- Strong prompt adherence and composition accuracy
- Next generation architecture beyond standard diffusion
- Local experimentation with the future of image models
GLM-Image first plans the image as tokens, then renders through diffusion. This two stage design improves composition, structure, and instruction following compared to traditional diffusion models.
FREE for all Farm Hand Members.
Setup Instructions
- Download the ZIP from the link above
- Extract the setup folder
- Place the BAT file outside your ComfyUI directory
- Run the setup
- Load the GLM-Image workflow in ComfyUI
Requirements
- Windows 10 or Windows 11
- NVIDIA GPU with 24GB VRAM recommended
- ComfyUI set up
Get Going Fast provides community setup guidance, documentation, tutorials, troubleshooting support, and member services. Get Going Fast does not sell, host, store, mirror, or redistribute AI model files, model weights, training datasets, or third-party project files.
When a setup guide references third-party dependencies, repositories, or model files, it points users to official upstream public sources such as GitHub, Hugging Face, package managers, or original project repositories, subject to those sources' own licenses, terms, and availability.
Get Going Fast is a general-audience AI education and workflow site, not an adult-content site or hosted AI generation service. Do not use Get Going Fast materials, support, guidance, or referenced third-party tools for unlawful, abusive, non-consensual, sexually explicit, exploitative, harassing, deceptive, or privacy-violating content, including misuse of another person's likeness, voice, identity, intellectual property, privacy, or publicity rights. See our Acceptable Use Policy.
If you are a rights holder, platform reviewer, payment processor, or hosting provider with a concern about a listed tool, guide reference, or upstream source, please contact us. We will review the concern promptly and remove or revise references when appropriate.
