Skip to content
PipeListedHosted

Z-Image: Text to image

Generate square images from text using the fixed Z-Image base model and Qwen text encoder. Generated images are returned through Sweet Tea's image preview output.

Workflow details

FamilyZ-ImageResolution1024x1024Estimated VRAMNot yet characterizedPublisherSweet Tea AutomationUpdatedOct 26Bgrade

Runtime profile

Publisher
Sweet Tea Automation
Status
Listed
Version
Checking published version…
Updated
Oct 26, 2026

Hover nodes for Pipe controls

Core

Primary Pipe surface

Positive prompt

CLIPTextEncode

Negative prompt

CLIPTextEncode

Image count

EmptySD3LatentImage

Sampling

KSampler

Extended

Additional surfaced controls

Noise schedule shift

ModelSamplingAuraFlow

What you need

Model files
0.3 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Output

  • Sweet Tea Preview Image · image

Requirements

Models

3

  • ae.safetensors

    Found

    VAE · 320 MB · SAFETENSORS · Hugging Face · Comfy-Org/z_image_turbo

  • qwen_3_4b.safetensors

    Found

    Text encoder · 7.49 GB · SAFETENSORS · Hugging Face · Comfy-Org/z_image_turbo

  • z_image_bf16.safetensors

    Found

    Checkpoint · 11.5 GB · SAFETENSORS · bf16 · full · Hugging Face · Comfy-Org/z_image

Node packs

1

Sources

1 source
Sweet TeaSource