Sign In

Z-Image Turbo — Free Lite T2I (8 Steps, 6 GB Cards) — ComfyUI

Download

1 variant available

Archive Other

Z_Image_Turbo_Base_Pack_Civitai_Free.zip

2.45 KB

Verified:

Type
Workflows
Stats

14

Reviews
Published

Nov 16, 2026

Base Model
Hash
AutoV29D51A62577
cover.jpg

FREE starter on Whop (lite workflow + exclusive cheat sheet): https://whop.com/imagelab/free-starter-z-image-turbo-base

FULL pack ($39): https://whop.com/imagelab/z-image-turbo-base-8-step-images-on-6-gb-cards-posters-2k-comfyui — use code ZIMG30 for 30% off ($39 → $27.30)

## FREE vs FULL

| | FREE (this download) | FULL ($39) |

|---|---|---|

| Workflows | 1 — Turbo text-to-image | 4 — Turbo + GGUF low-VRAM + Base 50-step + poster 2K |

| Low-VRAM GGUF (4–6 GB cards) | — | Yes |

| Base quality workflow | — | Yes |

| Poster + 2K upscale | — | Yes |

| Prompt library | — | 10 formulas + text tips |

| Guides | This README | Full EN quickstart + Arabic guide |

## What this is

Z-Image Turbo (Alibaba Tongyi-MAI) is a 6B distilled image model with 1.06M monthly downloads: 8 steps, no CFG, and it runs on 6 GB cards. This free lite workflow is the core text-to-image graph — BF16, 1024×1024, ready to run in ComfyUI.

## Files you need (not included)

From Comfy-Org/Z-Image-Turbo: z_image_turbo_bf16.safetensors (12.31 GB) → diffusion_models, qwen_3_4b.safetensors (8.04 GB) → text_encoders, ae.safetensors (0.34 GB) → vae. ~16 GB VRAM.

## License

Apache 2.0 — fully commercial. Strictly SFW.