Generated reference · ComfyUI workflow · Flagship (frontier)

Z-Image Sacred Art

Flagship 2026-generation sacred artwork on Z-Image-Turbo (6B S3-DiT, Apache 2.0): 8-step distilled sampling at cfg 1.0 with prose prompting.

Flagship (frontier)9nodesGPU L40Sout image~6sv1.0.0
workflow.json
On this page
9Graph nodes
8Node classes
6Inputs
3Models

Tags: flagshipz-imagesacred artmandala2026-sota

Inputs (6)#

The typed parameter surface callers bind when they request this workflow. Enum options and numeric bounds are the values the workflow document declares.

promptstringdefault an intricate sacred mandala radiating golden light
Subject description (prose works best on flow models)
styleenumdefault tibetan
Sacred-art tradition
options: tibetanhindubuddhistcelticislamicmodernvisionary
color_paletteenumdefault gold_sacred
Palette direction
options: chakra_rainbowgold_sacredearth_tonescosmic_bluelotus_pink
aspectenumdefault square_1024
Output aspect preset
options: square_1024landscape_1152x896portrait_896x1152
stepsintegerdefault 8min 4max 12
Turbo-distilled sampling steps (8 is the reference)
seedintegerdefault -1
Random seed (-1 for random)

ComfyUI node graph (9)#

The executable ComfyUI prompt graph: 9 nodes across 8 distinct node classes, wired by 9 data dependencies. Nodes tinted green come from a custom node pack this workflow declares; the rest are ComfyUI core / baked-community classes.

flowchart TD n0["1: UNETLoader"] n1["2: CLIPLoader"] n2["3: VAELoader"] n3["4: ModelSamplingAuraFlow"] n4["5: CLIPTextEncode"] n5["6: CLIPTextEncode"] n6["7: EmptySD3LatentImage"] n7["8: KSampler"] n8["9: VAEDecode"] n0 -->|model| n3 n1 -->|clip| n4 n1 -->|clip| n5 n3 -->|model| n7 n4 -->|positive| n7 n5 -->|negative| n7 n6 -->|latent_image| n7 n7 -->|samples| n8 n2 -->|vae| n8
Data-flow DAG — scroll to zoom, drag to pan.

Nodes (9)#

1UNETLoadercore
unet_name = z_image_turbo_bf16.safetensorsweight_dtype = default
outputs: MODEL
2CLIPLoadercore
clip_name = qwen_3_4b.safetensorstype = lumina2
outputs: CLIP
3VAELoadercore
vae_name = z_image_ae.safetensors
outputs: VAE
4ModelSamplingAuraFlowcore
model = ◂ node 1 · out[0]shift = 3.0
outputs: MODEL
5CLIPTextEncodecore
text = {{constructed_prompt}} tmplclip = ◂ node 2 · out[0]
outputs: CONDITIONING
6CLIPTextEncodecore
text = clip = ◂ node 2 · out[0]
outputs: CONDITIONING
7EmptySD3LatentImagecore
width = {{aspect_map[aspect].width}} tmplheight = {{aspect_map[aspect].height}} tmplbatch_size = 1
outputs: LATENT
8KSamplercore
model = ◂ node 4 · out[0]positive = ◂ node 5 · out[0]negative = ◂ node 6 · out[0]latent_image = ◂ node 7 · out[0]seed = {{seed}} tmplsteps = {{steps}} tmplcfg = 1.0sampler_name = res_multistepscheduler = simpledenoise = 1.0
outputs: LATENT
9VAEDecodecore
samples = ◂ node 8 · out[0]vae = ◂ node 3 · out[0]
outputs: IMAGE

Prompt construction#

template
A luminous sacred artwork: {base_prompt}, {style_prompt}, rendered in {color_prompt}. Perfect radial symmetry, fine detailed linework, museum lighting, high dynamic range.

Variables (3)#

base_prompt
{{prompt}} tmpl
style_prompt
{{style_prompts[style]}} tmpl
color_prompt
{{color_prompts[color_palette]}} tmpl

Parameter banks (3)#

The prompt / configuration lookup tables this workflow keys into from its inputs — the vocabulary that turns a style / palette / preset selection into graph parameters.

style_prompts (7)#

tibetan
in the tradition of Tibetan thangka sand painting, with lotus petals, a dharma wheel, and precise concentric geometry
hindu
as a Hindu sri yantra with interlocking triangles, a lotus throne, and sanskrit-inspired ornament
buddhist
as a serene Zen Buddhist composition with an enso circle, the eight auspicious symbols, and quiet negative space
celtic
woven from Celtic knotwork with trinity knots and endless interlace, illuminated-manuscript style
islamic
as Islamic geometric art with star polygons, arabesque interlace, and mathematically exact tiling
modern
as contemporary sacred geometry: the flower of life and metatron cube rendered with clean gradients
visionary
in visionary art style with translucent layers of light, subtle anatomy of energy bodies, and cosmic depth

color_prompts (5)#

chakra_rainbow
a full chakra spectrum flowing from deep red at the rim to violet at the crown center
gold_sacred
burnished gold leaf over deep lapis blue, candle-lit temple tones
earth_tones
natural mineral pigments: ochre, terracotta, moss, and bone
cosmic_blue
deep-space indigo and violet with silver starlight accents
lotus_pink
soft dawn rose and ivory with gentle warm highlights

aspect_map (3)#

square_1024
{"width": 1024, "height": 1024}
landscape_1152x896
{"width": 1152, "height": 896}
portrait_896x1152
{"width": 896, "height": 1152}

Models & dependencies#

Models required (3)#

z_image_turbo_bf16.safetensors
qwen_3_4b.safetensors
z_image_ae.safetensors

Output contract#

What a successful run of this workflow returns.

type
image
format
png

Taxonomy & routing#

How the control plane classifies this workflow — from the committed workflow-taxonomy-registry.json. It drives the consistency / control surface the agentic director can exercise over the workflow.

assetFamily
contemplative-sacred-art-bundle
outputPackageProfile
image-single-profile
controlModalities
model-lockpalette-locksampler-scheduler-lockseed-lockstyle-anchor
consistencyDimensions
color-scriptlighting
notes
Flagship 2026 sacred artwork on Z-Image-Turbo; prose prompting, 8-step distilled sampling.