Preview for Z-Image
Z-Image workflow diagram

Run this workflow on InstaSD

Get started in minutes! Run this ComfyUI workflow online - no setup required.

Description

Z-Image is an efficient 6-billion-parameter foundation model for image generation. Through systematic optimization, it proves that top-tier performance is achievable without relying on enormous model sizes, delivering strong results in photorealistic generation and bilingual text rendering.

Models

FileDestinationSource
qwen_3_4b.safetensors/ComfyUI/models/text_encodersDownload
ae.safetensors/ComfyUI/models/vaeDownload
z_image_turbo_bf16.safetensors/ComfyUI/models/diffusion_modelsDownload
qinglong_detailedeye_z-imageV2(comfy).safetensors/ComfyUI/models/lorasDownload

Nodes

CLIPLoaderVAELoaderConditioningZeroOutUNETLoaderEmptySD3LatentImageModelSamplingAuraFlowVAEDecodeCLIPTextEncodeLoraLoaderModelOnlyKSamplerSaveImage