Simple text-to-image workflow for Z-Image Turbo, tested on an RTX 5060 Ti 16 GB with 32 GB RAM in ComfyUI 0.38.1. Measured: 11.0 s per 1024×1024 image, peak VRAM 14.6 GB.
Files you need:
- z_image_turbo_bf16.safetensors → models/diffusion_models
- qwen_3_4b_fp8_mixed.safetensors → models/text_encoders
- ae.safetensors → models/vae
The note inside the workflow has a download link for every file.
Does it fit your card? https://vramready.com/models/z-image-turbo/
All tested workflows: https://vramready.com/workflows/
Description
Tested on RTX 5060 Ti 16 GB, 32 GB RAM, ComfyUI 0.38.1. 11.0 s per 1024×1024 image, peak VRAM 14.6 GB.