Generated reference · ComfyUI workflow · Sacred art

Mandala Generator

Generate sacred mandala artwork with symmetry, sacred geometry, and traditional styles

Sacred art13nodesGPU A5000out image~45sv1.0.0
workflow.json
On this page
13Graph nodes
11Node classes
14Inputs
3Models

Tags: mandalasacred geometrymeditationspiritualsymmetry

Inputs (14)#

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

promptstringdefault intricate sacred mandala, perfect circular symmetry, golden ratio proportions
Main prompt for mandala generation
negative_promptstringdefault asymmetric, blurry, low quality, text, watermark, signature, deformed
Negative prompt to avoid unwanted elements
styleenumdefault tibetan
Mandala tradition/style
options: tibetanhindubuddhistcelticislamicmodernpsychedelic
color_paletteenumdefault chakra_rainbow
Color palette for the mandala
options: chakra_rainbowgold_sacredearth_tonescosmic_bluelotus_pinkom_orangecustom
complexityenumdefault intricate
Level of detail and complexity
options: simplemoderateintricateultra_detailed
seedintegerdefault -1
Random seed (-1 for random)
widthintegerdefault 1024
Output width
heightintegerdefault 1024
Output height
stepsintegerdefault 30
Sampling steps
cfg_scalefloatdefault 7.5
CFG scale for prompt adherence
upscalebooleandefault true
Apply 4x upscaling
hires_fixbooleandefault true
Two-pass detail refinement: 1.5x latent upscale + low-denoise second sampling pass
freeubooleandefault true
FreeU v2 backbone re-weighting (family-tuned b1/b2/s1/s2)
checkpointenumdefault sdxl_base
SDXL checkpoint: curated photoreal finetune (default) or base 1.0
options: realvis_xl_v5sdxl_base

ComfyUI node graph (13)#

The executable ComfyUI prompt graph: 13 nodes across 11 distinct node classes, wired by 18 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: CheckpointLoaderSimple"] n1["2: CLIPTextEncode"] n2["3: CLIPTextEncode"] n3["4: EmptyLatentImage"] n4["5: KSampler"] n5["6: VAEDecode"] n6["7: ImageSymmetry"] n7["8: UpscaleModelLoader"] n8["9: ImageUpscaleWithModel"] n9["10: SaveImage"] n10["freeu: FreeU_V2"] n11["hires_upscale: LatentUpscaleBy"] n12["hires_sampler: KSampler"] n0 -->|clip| n1 n0 -->|clip| n2 n10 -->|model| n4 n1 -->|positive| n4 n2 -->|negative| n4 n3 -->|latent_image| n4 n12 -->|samples| n5 n0 -->|vae| n5 n5 -->|image| n6 n7 -->|upscale_model| n8 n6 -->|image| n8 n8 -->|images| n9 n0 -->|model| n10 n4 -->|samples| n11 n10 -->|model| n12 n1 -->|positive| n12 n2 -->|negative| n12 n11 -->|latent_image| n12
Data-flow DAG — scroll to zoom, drag to pan.

Nodes (13)#

1CheckpointLoaderSimplecore
ckpt_name = {{checkpoint_files[checkpoint]}} tmpl
outputs: MODELCLIPVAE
2CLIPTextEncodecore
text = {{constructed_prompt}} tmplclip = ◂ node 1 · out[1]
outputs: CONDITIONING
3CLIPTextEncodecore
text = {{negative_prompt}} tmplclip = ◂ node 1 · out[1]
outputs: CONDITIONING
4EmptyLatentImagecore
width = {{width}} tmplheight = {{height}} tmplbatch_size = 1
outputs: LATENT
5KSamplercore
model = ◂ node freeu · out[0]positive = ◂ node 2 · out[0]negative = ◂ node 3 · out[0]latent_image = ◂ node 4 · out[0]seed = {{seed}} tmplsteps = {{steps}} tmplcfg = {{cfg_scale}} tmplsampler_name = dpmpp_2m_sdescheduler = karrasdenoise = 1.0
outputs: LATENT
6VAEDecodecore
samples = ◂ node hires_sampler · out[0]vae = ◂ node 1 · out[2]
outputs: IMAGE
7ImageSymmetrycore
image = ◂ node 6 · out[0]symmetry_type = radial_8blend_mode = multiply
outputs: IMAGE
8UpscaleModelLoadercore
model_name = RealESRGAN_x4plus.pth
outputs: UPSCALE_MODEL
9ImageUpscaleWithModelcore
upscale_model = ◂ node 8 · out[0]image = ◂ node 7 · out[0]
outputs: IMAGE
10SaveImagecore
images = ◂ node 9 · out[0]filename_prefix = mandala
freeuFreeU_V2core
model = ◂ node 1 · out[0]b1 = 1.1b2 = 1.2s1 = 0.6s2 = 0.4
outputs: MODEL
hires_upscaleLatentUpscaleBycore
samples = ◂ node 5 · out[0]upscale_method = bislerpscale_by = 1.5
outputs: LATENT
hires_samplerKSamplercore
model = ◂ node freeu · out[0]positive = ◂ node 2 · out[0]negative = ◂ node 3 · out[0]latent_image = ◂ node hires_upscale · out[0]seed = {{seed}} tmplsteps = 14cfg = {{cfg_scale}} tmplsampler_name = dpmpp_2mscheduler = karrasdenoise = 0.45
outputs: LATENT

Prompt construction#

template
{base_prompt}, {style_prompt}, {color_prompt}, {complexity_prompt}, highly detailed, circular composition, radial symmetry, sacred art

Variables (4)#

base_prompt
{{prompt}} tmpl
style_prompt
{{style_prompts[style]}} tmpl
color_prompt
{{color_prompts[color_palette]}} tmpl
complexity_prompt
{{complexity_prompts[complexity]}} 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
tibetan buddhist mandala, sand painting style, lotus petals, dharma wheel, traditional thangka colors, sacred buddhist symbolism
hindu
hindu yantra mandala, sri yantra geometry, gold and red tones, lotus throne, om symbol, sanskriti patterns
buddhist
zen buddhist enso mandala, dharma wheel, eight auspicious symbols, lotus flower, peaceful meditation imagery
celtic
celtic knot mandala, interlaced patterns, trinity knot, endless knot, green and gold, ancient druid symbolism
islamic
islamic geometric mandala, arabesque patterns, star polygon, muqarnas, turquoise and gold, mathematical precision
modern
modern sacred geometry mandala, flower of life, metatron's cube, platonic solids, gradient colors, digital art style
psychedelic
psychedelic visionary mandala, fractal patterns, alex grey style, consciousness expansion, vibrant neon colors, cosmic energy

color_prompts (7)#

chakra_rainbow
rainbow chakra colors, red orange yellow green blue indigo violet gradient
gold_sacred
gold and deep blue, sacred gold leaf, royal colors, divine light
earth_tones
earthy brown ochre terracotta, natural pigments, sand colors
cosmic_blue
deep space blue purple, cosmic nebula colors, starlight silver
lotus_pink
pink lotus petals, soft rose and white, gentle dawn colors
om_orange
sacred saffron orange, temple incense gold, warm spiritual tones
custom

complexity_prompts (4)#

simple
clean minimal design, basic geometric forms, elegant simplicity
moderate
balanced detail, clear patterns, refined ornamentation
intricate
highly detailed, complex layered patterns, fine line work
ultra_detailed
extremely intricate, microscopic detail, countless tiny elements, masterwork precision

Models & dependencies#

Checkpoint aliases (2)#

realvis_xl_v5
RealVisXL_V5.0_fp16.safetensors
sdxl_base
sd_xl_base_1.0.safetensors

Models required (3)#

RealESRGAN_x4plus.pth
RealVisXL_V5.0_fp16.safetensors
sd_xl_base_1.0.safetensors

Output contract#

What a successful run of this workflow returns.

type
image
format
png
channels
4
expected_dimensions
{"width": "{{width * (4 if upscale else 1)}}", "height": "{{height * (4 if upscale else 1)}}"}

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
mkt-brand-style-lock-template-pack
outputPackageProfile
image-single-profile
controlModalities
color-script-lockmodel-lockprompt-template-locksampler-scheduler-lockseed-lockstyle-lock
consistencyDimensions
lightingcolor-script
notes
Auto-mapped from sacred-art defaults