Generated reference · ComfyUI workflow · 3D reconstruction

Sacred Artifact 3D Reconstruction

Generate multi-view images of sacred artifacts for 3D reconstruction, optimized for spiritual and historical objects

3D reconstruction10nodesGPU A6000out 3d_model~240sv1.0.0

On this page
10Graph nodes
9Node classes
10Inputs
1Models

Tags: 3dartifactsacredreconstructionmultiviewhistorical

Inputs (10)#

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

reference_imageimagerequired
Reference image of the artifact
artifact_categoryenumdefault statue_deity
Category of sacred artifact
options: statue_deityritual_objectsacred_vesselmeditation_toolancient_reliccrystal_formationsacred_texttemple_elementmandala_3dceremonial_mask
material_typeenumdefault stone
Primary material of the artifact
options: stonebronzegoldsilverwoodjadecrystalclaymixed
era_styleenumdefault universal_sacred
Cultural/historical era style
options: ancient_egyptiangreco_romanbuddhisthindumesoamericancelticafricaneast_asianmiddle_easternuniversal_sacred
surface_conditionenumdefault aged_patina
Surface condition of the artifact
options: pristineaged_patinaweatheredpartially_damagedmuseum_restored
view_coverageenumdefault standard_8_views
Coverage of viewing angles
options: quick_4_viewsstandard_8_viewsfull_12_views
lighting_styleenumdefault museum_lighting
Lighting style for the views
options: museum_lightingnatural_daylightdramatic_spotlightsoft_diffusearchaeological_documentation
include_detailsbooleandefault true
Include close-up detail views
output_resolutionenumdefault 768x768
Resolution of output views
options: 512x512768x7681024x1024
seedintegerdefault -1
Random seed

ComfyUI node graph (10)#

The executable ComfyUI prompt graph: 10 nodes across 9 distinct node classes, wired by 14 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: LoadImage"] n1["2: ImageScale"] n2["3: BackgroundRemover"] n3["4: ImageOnlyCheckpointLoader"] n4["5: StableZero123_Conditioning_Batched"] n5["6: KSampler"] n6["7: VAEDecode"] n7["8: SaveImage"] n8["9: CreateDocumentationGrid"] n9["10: SaveImage"] n0 -->|image| n1 n1 -->|image| n2 n3 -->|clip_vision| n4 n2 -->|init_image| n4 n3 -->|vae| n4 n3 -->|model| n5 n4 -->|positive| n5 n4 -->|negative| n5 n4 -->|latent_image| n5 n5 -->|samples| n6 n3 -->|vae| n6 n6 -->|images| n7 n6 -->|images| n8 n8 -->|images| n9 classDef custom fill:#12b886,stroke:#0b6b4f,color:#04110c; class n2,n8 custom;
Data-flow DAG — scroll to zoom, drag to pan.

Nodes (10)#

1LoadImagecore
image = {{reference_image}} tmpl
outputs: IMAGEMASK
2ImageScalecore
image = ◂ node 1 · out[0]upscale_method = lanczoswidth = 256height = 256crop = center
outputs: IMAGE
3BackgroundRemovercustom pack
image = ◂ node 2 · out[0]mode = neutral_gray
outputs: IMAGEMASK
4ImageOnlyCheckpointLoadercore
ckpt_name = stable_zero123.ckpt
outputs: MODELCLIP_VISIONVAE
5StableZero123_Conditioning_Batchedcore
clip_vision = ◂ node 4 · out[1]init_image = ◂ node 3 · out[0]vae = ◂ node 4 · out[2]width = 256height = 256batch_size = {{view_coverage_configs[view_coverage].count}} tmplelevation = {{view_coverage_configs[view_coverage].elevation}} tmplazimuth = 0.0elevation_batch_increment = 0.0azimuth_batch_increment = {{view_coverage_configs[view_coverage].azimuth_increment}} tmpl
outputs: positivenegativelatent
6KSamplercore
model = ◂ node 4 · out[0]positive = ◂ node 5 · out[0]negative = ◂ node 5 · out[1]latent_image = ◂ node 5 · out[2]seed = {{seed}} tmplsteps = 20cfg = 4.0sampler_name = eulerscheduler = sgm_uniformdenoise = 1.0
outputs: LATENT
7VAEDecodecore
samples = ◂ node 6 · out[0]vae = ◂ node 4 · out[2]
outputs: IMAGE
8SaveImagecore
images = ◂ node 7 · out[0]filename_prefix = artifact_view
9CreateDocumentationGridcustom pack
images = ◂ node 7 · out[0]style = museum_catalogcaption = {{artifact_category}} — {{material_type}}, {{era_style}} ({{surface_condition}}) tmpl
outputs: IMAGE
10SaveImagecore
images = ◂ node 9 · out[0]filename_prefix = artifact_documentation

Prompt construction#

template
3D artifact documentation, {artifact_prompt}, {material_prompt}, {era_prompt}, {condition_prompt}, {lighting_prompt}, museum quality photography, archival documentation, consistent views, professional 3D asset, detailed texture capture

Variables (5)#

artifact_prompt
{{artifact_prompts[artifact_category]}} tmpl
material_prompt
{{material_prompts[material_type]}} tmpl
era_prompt
{{era_prompts[era_style]}} tmpl
condition_prompt
{{condition_prompts[surface_condition]}} tmpl
lighting_prompt
{{lighting_prompts[lighting_style]}} tmpl

Parameter banks (8)#

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

artifact_prompts (10)#

statue_deity
sacred statue of deity, religious figure, devotional sculpture, divine representation
ritual_object
ritual object, ceremonial item, sacred tool, spiritual implement
sacred_vessel
sacred vessel, ritual container, ceremonial bowl, offering vessel
meditation_tool
meditation tool, prayer object, contemplative aid, spiritual practice item
ancient_relic
ancient relic, historical artifact, archaeological treasure, antique sacred object
crystal_formation
sacred crystal formation, spiritual stone, power crystal, natural gem formation
sacred_text
sacred text object, religious manuscript, prayer scroll, spiritual scripture artifact
temple_element
temple architectural element, sacred building detail, shrine component
mandala_3d
three-dimensional mandala, sacred geometric structure, spiritual diagram object
ceremonial_mask
ceremonial mask, ritual face covering, sacred mask, spiritual visage

material_prompts (9)#

stone
carved stone, marble or granite texture, mineral surface, sculpted rock
bronze
cast bronze, oxidized metal, green patina, metal sculpture
gold
gold material, gilded surface, precious metal, golden finish
silver
silver material, polished metal, sacred silver, moonlit metal
wood
carved wood, natural grain, sacred timber, wooden sculpture
jade
jade material, green stone, precious mineral, nephrite or jadeite
crystal
crystal material, transparent or translucent, quartz or gemstone
clay
fired clay, terracotta, ceramic material, earthen sculpture
mixed
mixed materials, composite construction, multiple mediums

era_prompts (10)#

ancient_egyptian
ancient Egyptian style, hieroglyphic influence, pharaonic aesthetic
greco_roman
Greco-Roman style, classical antiquity, Mediterranean aesthetic
buddhist
Buddhist artistic style, dharma influence, enlightenment aesthetic
hindu
Hindu artistic style, vedic influence, divine aesthetic
mesoamerican
Mesoamerican style, Aztec or Mayan influence, pre-Columbian aesthetic
celtic
Celtic style, knotwork patterns, insular art influence
african
African artistic style, tribal influence, ancestral aesthetic
east_asian
East Asian style, Chinese or Japanese influence, oriental aesthetic
middle_eastern
Middle Eastern style, Islamic or Persian influence, arabesque aesthetic
universal_sacred
universal sacred style, cross-cultural spiritual aesthetic

condition_prompts (5)#

pristine
pristine condition, like new, perfectly preserved, museum quality
aged_patina
aged patina, natural aging, authentic wear, historical character
weathered
weathered surface, exposed to elements, natural erosion, time-worn
partially_damaged
partially damaged, missing elements, archaeological state
museum_restored
museum restored, conservation treatment, professional preservation

lighting_prompts (5)#

museum_lighting
museum lighting, professional display illumination, even coverage, archival quality
natural_daylight
natural daylight, outdoor illumination, sun-lit, authentic lighting
dramatic_spotlight
dramatic spotlight, focused illumination, artistic lighting, gallery presentation
soft_diffuse
soft diffuse lighting, gentle illumination, shadow-free, clear visibility
archaeological_documentation
archaeological documentation lighting, scientific accuracy, field recording style

view_configurations (4)#

front_focused
{"views": 6, "emphasis": "front and slight variations", "angles": ["front", "front_left", "front_right", "front_top", "front_bottom", "detail"]}
full_rotation
{"views": 12, "emphasis": "complete 360 coverage", "angles": ["front", "front_right", "right", "back_right", "back", "back_left", "left", "front_left", "top", "bottom", "detail_1", "detail_2"]}
detailed_angles
{"views": 16, "emphasis": "comprehensive with details", "angles": ["front", "front_right_30", "right", "back_right_30", "back", "back_left_30", "left", "front_left_30", "top_front", "top_back", "bottom", "detail_face", "detail_hands", "detail_base", "detail_inscription", "detail_texture"]}
documentation_standard
{"views": 8, "emphasis": "archival documentation", "angles": ["front", "back", "left", "right", "top", "bottom", "three_quarter_front", "three_quarter_back"]}

resolution_map (3)#

512x512
{"width": 512, "height": 512}
768x768
{"width": 768, "height": 768}
1024x1024
{"width": 1024, "height": 1024}

view_coverage_configs (3)#

quick_4_views
{"count": 4, "azimuth_increment": 90.0, "elevation": 0.0}
standard_8_views
{"count": 8, "azimuth_increment": 45.0, "elevation": 0.0}
full_12_views
{"count": 12, "azimuth_increment": 30.0, "elevation": 10.0}

Models & dependencies#

Custom node packs (2)#

The non-core ComfyUI node classes this graph requires; the RunPod worker image the workflow runs on must bake or install a pack that provides every one of them.

BackgroundRemoverCreateDocumentationGrid

Models required (1)#

stable_zero123.ckpt

Output contract#

What a successful run of this workflow returns.

type
3d_model
format
glb
primary
{"type": "3d_model", "format": "glb", "description": "Primary reconstructed 3D mesh package"}
secondary
{"type": "image_sequence", "format": "png", "description": "Multi-view documentation frames for QA and turntable review"}
metadata
{"type": "json", "description": "View angles and artifact information"}
three_d_package
{"mesh": {"artifact_id": "mesh", "path_template": "mesh/{{job_id}}/artifact.glb", "format": "glb", "unit_scale_meters": 1, "up_axis": "y", "target_triangle_budget": 180000, "lods": [{"name": "lod0", "path_template": "mesh/{{job_id}}/lod0.glb", "target_triangle_count": 180000}, {"name": "lod1", "path_template": "mesh/{{job_id}}/lod1.glb", "target_triangle_count": 90000}]}, "materials": {"artifact_id": "materials", "path_template": "materials/{{job_id}}/materials.json", "format": "json", "workflow": "metallic-roughness", "max_material_count": 12}, "textures": {"artifact_id": "textures", "path_template": "textures/{{job_id}}/{slot}.png", "format": "png", "required_slots": ["base_color", "normal", "roughness", "metallic", "occlusion"], "optional_slots": ["emissive", "opacity", "height"], "default_resolution": {"width": 2048, "height": 2048}}, "metadata": {"artifact_id": "metadata", "path_template": "metadata/{{job_id}}/manifest.json", "format": "json", "manifest_version": "1.0.0"}, "preview_turntable": {"artifact_id": "preview_turntable", "path_template": "preview/{{job_id}}/turntable.mp4", "format": "mp4", "duration_seconds": 8, "fps": 24}}

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
film-prop-lookdev-turntable
outputPackageProfile
game-ready-3d-profile
controlModalities
camera-lockcamera-path-guidecontrolnet-depthcontrolnet-normaldepth-constraintidentity-adapterlatent-reuselens-profile-lockmodel-lockpalette-lockpose-constraintreference-ensemblesampler-scheduler-lockscene-lockseed-lockstyle-anchor +2 more
consistencyDimensions
propenvironmentlightinglens
notes
3D reconstruction flow mapped to prop turntable and reconstruction controls.