Diffusion model
z_image_ bf16. safetensors
Z Image BF16 · Diffusion model for ComfyUI
- File
z_image_bf16.safetensors- Type
- Diffusion model
- Size
- 12.3 GB
- Folder
ComfyUI/models/diffusion_models/- Source
- Comfy-Org/Z-Image
- SHA-256
996a67d3ff66…
1 workflow uses this file
What is Z Image BF16?
Z Image BF16 is a diffusion model, the core network that turns your prompts into the output. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Z Image BF16 with other models and custom nodes to build any pipeline you need. There is 1 official ComfyUI workflow template that uses Z Image BF16, ready to load and customize.
Read the full tutorial →Workflows for this file
- Z-Image
Z-Image: Text to Image
Uses this file - Z-Image-Turbo
Z-Image-Turbo Text to Image
- Flux, Flux.2 Klein
Flux.2 [Klein] 4B Distilled: Image Edit
- Flux, Flux.2 Dev
Flux.2 Dev: Image Edit
- Flux, Flux.2 Klein
Flux.2 [Klein] 9B: Image Edit
- Flux, Flux.2 Dev
Flux.2 Dev Text to Image
- Z-Image-Turbo
Z-Image-Turbo Fun Union ControlNet
- Flux, Flux.1
Flux.1 Inpaint
Frequently Asked Questions
Z Image BF16 is a diffusion model, the core network that turns your prompts into the output. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Z Image BF16 with other models and custom nodes to build any pipeline you need. There is 1 official ComfyUI workflow template that uses Z Image BF16, ready to load and customize.
Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/image/z-image/z-image. You can also load the official ComfyUI workflow template that uses Z Image BF16 directly in ComfyUI.
There is 1 official ComfyUI workflow template that uses Z Image BF16. It is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Z Image BF16 weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.