Z-Image Turbo in ComfyUI: Realism at Lightning Speed
A 6B text-to-image model built for high-fidelity, hyper-realistic portraits.
- VRAM
- Low VRAM (≤8GB)
- Reading Time
- 2 min
Workflow Overview
A 6B text-to-image model built for high-fidelity, hyper-realistic portraits.
Content type: Workflow
Primary intent: Download
Setup Notes
- Install the required models before opening the workflow template.
- Recommended hardware: Low VRAM (≤8GB).
- Use the download button above to import the workflow JSON into ComfyUI.
Z-Image Turbo: Efficient Image Generation Model Overview
Developed by Alibaba Tongyi Research, the Z-Image framework stands as a potent and streamlined image synthesis tool with 6 billion parameters, aimed at crafting superior visuals. Its refined version, Z-Image-Turbo, has been tailored for smooth operation on standard 16GB VRAM GPUs while preserving outstanding performance, notably in producing lifelike images with sharp specifics.
A full, uncompressed variant will soon be made available, encouraging community fine-tuning and broader ecosystem development across open-source platforms.
Starting Process for Local ComfyUI Users
Ensure ComfyUI is updated to the latest version.
Download the workflow file and integrate it directly into ComfyUI.
Fetch the necessary models per the workflow guidelines and proceed with execution:
Z-Image Turbo Workflow
Sample Output Showcase
Achieving rapid generation speeds: 4.8 seconds for a 2K image on an NVIDIA RTX Pro 6000 Blackwell.
Image Samples

Caption: Depiction of a female figure with voluminous hair set against boats and houses at a harbor. Embrace a seaside atmosphere with gentle breezes and warm-hued lighting in a tightly framed shot.

Caption: Lifelike close-up capturing a beautiful woman in a fur hat, her finger adorned by a vibrant blue butterfly, cast in cinematic shadow-play for heightened realism.

Caption: Illustration of a female subject styled for urban travel, against a backdrop of motion-blurred city crowds amidst luminous billboards.

Caption: Evocative interpretation showcasing a Japanese woman glancing over her shoulder in a car’s rear, draped in a kimono complemented by tenderness in mood lighting.

Caption: Crisp portrayal of someone equipped for hiking amid woods, highlighted by late-day rays against defined facial contours.

Caption: Close-up portrait emphasizing a determined hiker amidst mountainous terrain, attention on detailed accessories and lighting interplay.

Caption: Sunny depiction near the water’s edge, framed by textured hair glistening in backlight during the golden hour.