Z-Image Turbo text to image
Create images from a text description using the fixed Z-Image Turbo INT8 model, Qwen text encoder and paired VAE. No uploaded image is required.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 25, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Image prompt
CLIPTextEncode
Output size and count
EmptySD3LatentImage
Extended
Additional surfaced controls
Sampling
KSampler
Noise schedule
ModelSamplingAuraFlow
What you need
- Model files
- 0.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Guides for this recipe
Output
- Generated images · image
Requirements
Models
3- Found
VAE · 320 MB · SAFETENSORS · Hugging Face · Comfy-Org/z_image_turbo
qwen_3_4b_fp8_mixed.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/z_image_turbo
z_image_turbo_int8_convrot.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/z_image_turbo
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source