Eve library

ISIS v2 Social Cutdown Pack Baseline Workflow Graph

Guide

Revision 1

On this page

Generated: 2026-08-02T19:12:23.235Z Checklist: MXA-0506 (ISIS2-00704) Asset Family: social-cutdown-pack Phase: Phase 4 | Milestone: M3 Launch (2026-07-27 to 2026-10-30)

Objective#

Provide a deterministic baseline workflow graph for social-cutdown-pack generation with locked sampler/model defaults, reproducible framing defaults, and delivery-ready output topology.

Deterministic Defaults#

Setting Value
checkpointModel sd_xl_base_1.0.safetensors
seed 2026072901
width 1080
height 1920
steps 32
cfgScale 6.4
samplerName dpmpp_2m_sde
scheduler karras
denoise 1
batchSize 1
outputFormat png
outputChannels 4

Input Contract#

Input Type Required Default
campaign_id string yes SOCIAL_M3_CUTDOWN_01
source_asset_id string yes asset://masters/campaign-master-hero-001
narrative_goal string yes Deliver a punchy hero cutdown that preserves subject clarity and message focus.
platform_target enum yes instagram-reels
aspect_ratio enum yes 9:16
hook_window_seconds float yes 1.8
cutdown_duration_seconds float yes 9.5
caption_safe_area enum yes lower-third
style_preset enum yes punchy-social
brand_palette string yes primary:#0F3DFF secondary:#FF6A00 accent:#F5F2E8
audio_sync_profile enum yes beat-emphasis
seed integer yes 2026072901
width integer yes 1080
height integer yes 1920
steps integer yes 32
cfg_scale float yes 6.4

Graph Nodes#

Node ID Class Role Output Count
n1 CheckpointLoaderSimple model-load 3
n2 CLIPTextEncode positive-conditioning 1
n3 CLIPTextEncode negative-conditioning 1
n4 EmptyLatentImage latent-init 1
n5 KSampler latent-sample 1
n6 VAEDecode image-decode 1
n7 SaveImage artifact-output 0

Graph Edges#

Edge ID From To
e1 n1:0 n5.model
e2 n1:1 n2.clip
e3 n1:1 n3.clip
e4 n1:2 n6.vae
e5 n2:0 n5.positive
e6 n3:0 n5.negative
e7 n4:0 n5.latent_image
e8 n5:0 n6.samples
e9 n6:0 n7.images

Topological Node Order#

n1 -> n2 -> n3 -> n4 -> n5 -> n6 -> n7

Research Alignment#

Workflow Path Node Classes
Print-Ready NFT Artwork Generator libs/isis/workflows/src/workflows/nft/print-ready.json CalculatePrintDimensions, ColorProfileConverter, LoadImage, PaperSimulation, PrintProofMarks, PrintReadyUpscaler, PrintSharpening, SaveImage, SavePrintReadyImage, UpscaleModelLoader
AI Style Transfer libs/isis/workflows/src/workflows/utility/style-transfer.json CLIPTextEncode, CheckpointLoaderSimple, ColorTransfer, ControlNetApply, ControlNetLoader, IPAdapter, IPAdapterUnifiedLoader, KSampler, LineArtPreprocessor, LoadImage, SaveImage, VAEDecode, VAEEncode
Barnsley Fern Generator libs/isis/workflows/src/workflows/fractal/barnsley-fern.json CLIPTextEncode, CheckpointLoaderSimple, EmptyLatentImage, FreeU_V2, KSampler, LatentUpscaleBy, SaveImage, VAEDecode

Acceptance Criteria#

  • Graph is acyclic and topologically sortable.
  • All deterministic defaults are explicitly set (seed, sampler, scheduler, checkpoint).
  • Node class inventory covers baseline generation path from prompt conditioning to persisted social cutdown output frame.
  • Output contract aligns to MXA-0505 required output classes.

Traceability#

  • Checklist item: MXA-0506
  • Ticket key: ISIS2-00704
  • Source references:
    • docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json
    • docs/domains/isis/remediation-v2/ISIS_V2_SOCIAL_CUTDOWN_PACK_REQUIREMENTS_BRIEF.json
    • libs/isis/workflows/src/workflows/nft/print-ready.json
    • libs/isis/workflows/src/workflows/utility/style-transfer.json
    • libs/isis/workflows/src/workflows/fractal/barnsley-fern.json
    • docs/domains/isis/remediation-v2/ISIS_V2_CONTROL_TAXONOMY.json
    • docs/domains/isis/remediation-v2/ISIS_V2_OUTPUT_PACKAGE_TAXONOMY.json
    • ISIS_TODOS_2.md