Nodes/ComfyUI-ZImageDit/Z-Image Generate (SDNQ)
ComfyUI Node

Z-Image Generate (SDNQ)

A ComfyUI node in Z-Image (SDNQ) with 16 inputs and 1 output.

By erosDiffusion·Created 9 months ago·Updated 8 months ago· 5
Z-Image Generate (SDNQ)
  • pipeline
  • input_image
  • IMAGE
prompta beautiful landscape
resolution_preset1024x1024 ( 1:1 )
num_inference_steps9
guidance_scale0.0
seed42
shift3.0
max_sequence_length1024
noise_scale1.00
strength0.75
custom_width1024
custom_height1024
enhance_promptfalse
unload_after_generationfalse
gc_cudafalse
CategoryZ-Image (SDNQ)

Inputs (16)

NameTypeDefaultDescription
pipelineZIMAGE_SDNQ_PIPELINE
promptSTRINGa beautiful landscapeText description of the image to generate. Be descriptive for best results
resolution_presetCOMBO1024x1024 ( 1:1 )Select a resolution preset, 'use image size' to match input image dimensions, or 'custom' to set manual width/height
num_inference_stepsINT91–100Number of denoising steps. Z-Image Turbo is optimized for 5-9 steps. More steps = slower but potentially higher quality
guidance_scaleFLOAT0.00–20Classifier-free guidance scale. Z-Image Turbo is trained for guidance_scale=0.0 (recommended). Higher values increase prompt adherence but may reduce quality
seedINT420–18446744073709550000Random seed for reproducible generation. Same seed + settings = same image
shiftFLOAT3.01–10Time shift for FlowMatch scheduler. Controls sampling distribution: lower (1-2) = more noise-end sampling, higher (4-10) = more clean-end sampling. Default 3.0 is balanced
max_sequence_lengthINT1024128–2048Maximum prompt token length. 1024 recommended for detailed prompts (Z-Image works best with long descriptions). 512 for faster speed
noise_scaleFLOAT1.000–2Scale for initial noise. 1.0 = normal random noise, lower = less variation, higher = more variation. Only affects pure noise (not image latents)
strengthFLOAT0.750–1Denoising strength for img2img. 0.0 = no change (pure image), 1.0 = full regeneration (ignore image). Only applies when input_image is provided. Controls how many timesteps to denoise
input_imageoptIMAGEOptional input image to encode to latents. Will be blended with noise based on noise_scale. Use 'use image size' preset to match image dimensions
custom_widthoptINT1024256–2048Custom output width (only used when resolution_preset is 'custom'). Must be divisible by 64
custom_heightoptINT1024256–2048Custom output height (only used when resolution_preset is 'custom'). Must be divisible by 64
enhance_promptoptBOOLEANfalseUse Z-Image's built-in prompt enhancer for improved semantic understanding and detail. May not be available in all models
unload_after_generationoptBOOLEANfalseMove models to CPU after generation to free VRAM. Useful for memory-constrained setups
gc_cudaoptBOOLEANfalseRun Python garbage collection and clear CUDA cache after generation. Helps reclaim memory

Outputs (1)

NameTypeDescription
IMAGEIMAGE