Z Image Turbo is a fast distilled diffusion model.
Text encoder file: qwen_3_4b.safetensors (goes in ComfyUI/models/text_encoders/).
diffusion model file: z_image_turbo_bf16.safetensors (goes in ComfyUI/models/diffusion_models/).
VAE: ae.safetensors the Flux 1 VAE if you don’t have it already (goes in ComfyUI/models/vae/)
You can then load up or drag the following image in ComfyUI to get the workflow:
