Eve library

ISIS v2 Audio SFX Pack Image-Conditioned Workflow Graph

Guide

Revision 1

On this page

Generated: 2026-08-02T19:12:25.946Z Checklist: MXA-0525 (ISIS2-00723) Asset Family: audio-sfx-pack Phase: Phase 4 | Milestone: M3 Launch (2026-07-27 to 2026-10-30)

Objective#

Define an image-conditioned audio-sfx-pack workflow graph that maps image-conditioning requirements to provider-capable reference-audio guidance while preserving deterministic synthesis defaults and mastered-audio delivery contracts.

Deterministic Defaults#

Setting Value
modelName stable_audio_open_1.0.safetensors
promptTemplateId audio-sfx-pack-image-conditioned-v1
styleProfileId audio-sfx-pack-style-anchor-v1
seed 2026073102
durationSeconds 6
conditioningStrength 0.72
conditioningMode reference-audio
providerCapabilityMode required
referenceMixStrategy weighted-blend
maxReferenceCount 4
preservePromptIntent true
sampleRateHz 48000
targetLufs -16
outputFormat wav
outputChannels 2
outputBitDepth 24

Input Contract#

Input Type Required Default
cue_id string yes "AUDIO_SFX_M3_IMAGE_CONDITIONED_01"
prompt string yes "Heavy metal gate slam with a short resonant tail and cinematic impact."
sfx_type enum yes "impact"
intensity enum yes "strong"
spatial_profile enum yes "cinematic"
duration_seconds integer yes 6
audio_prompt_hint string no "Preserve crisp attack and low-end body from reference material."
reference_audio_url string yes "asset://references/audio/sfx-style-anchor-001.wav"
reference_audio_urls array no ["asset://references/audio/sfx-transient-anchor-002.wav","asset://references/audio/sfx-room-tail-anchor-003.wav"]
style_reference_id string no "AUDIO_SFX_STYLE_ANCHOR_V1"
conditioning_strength float yes 0.72
conditioning_mode enum yes "reference-audio"
provider_capability_mode enum yes "required"
reference_mix_strategy enum yes "weighted-blend"
preserve_prompt_intent boolean yes true
prompt_template_id string yes "audio-sfx-pack-image-conditioned-v1"
style_profile_id string yes "audio-sfx-pack-style-anchor-v1"
sample_rate_hz integer yes 48000
target_lufs float yes -16
output_format enum yes "wav"
model_name string yes "stable_audio_open_1.0.safetensors"
seed integer yes 2026073102

Graph Nodes#

Node ID Class Role Output Count
n1 LoadAudio primary-reference-load 1
n2 LoadAudio secondary-reference-load 1
n3 StableAudioPromptComposer prompt-construction 1
n4 StableAudioOpenModelLoader model-load 1
n5 AudioReferenceConditioner reference-conditioning 2
n6 StableAudioNode audio-generation 1
n7 AudioLoudnessNormalize audio-post 1
n8 SaveAudio artifact-output 0

Graph Edges#

Edge ID From To
e1 n1:0 n5.primary_reference
e2 n2:0 n5.secondary_references
e3 n3:0 n5.prompt
e4 n5:0 n6.conditioned_prompt
e5 n5:1 n6.reference_conditioning
e6 n4:0 n6.model
e7 n6:0 n7.audio
e8 n7:0 n8.audio

Topological Node Order#

n1 -> n2 -> n3 -> n4 -> n5 -> n6 -> n7 -> n8

Research Alignment#

Workflow Path Reference Conditioning Support Conditioning Input Keys Node Classes
SFX Sound Designer libs/isis/workflows/src/workflows/audio/sfx-sound-designer.json yes reference_audio_url, reference_audio_urls, conditioning_strength, conditioning_mode, provider_capability_mode AudioLoudnessNormalize, CLIPLoader, CLIPTextEncode, CheckpointLoaderSimple, EmptyLatentAudio, KSampler, SaveAudioMP3, VAEDecodeAudio
Music Cue Composer libs/isis/workflows/src/workflows/audio/music-cue-composer.json yes reference_audio_url, reference_audio_urls, conditioning_strength, conditioning_mode, provider_capability_mode AudioLimiter, CheckpointLoaderSimple, ConditioningZeroOut, EmptyAceStep1.5LatentAudio, KSampler, ModelSamplingAuraFlow, SaveAudioMP3, TextEncodeAceStepAudio1.5, VAEDecodeAudio
Voice Performance Synthesis libs/isis/workflows/src/workflows/audio/voice-performance-synthesis.json yes voice_profile AudioDeesser, AudioLoudnessNormalize, KokoroTextToSpeech, SaveAudio

Acceptance Criteria#

  • Graph is acyclic and topologically sortable.
  • Reference conditioning path is explicit and includes required primary reference audio and optional multi-reference stack.
  • Deterministic defaults are explicitly locked (seed, model, prompt template, style profile, conditioning mode/provider mode, loudness, and export format).
  • Output contract aligns to MXA-0523 required output classes for audio-sfx-pack.

Traceability#

  • Checklist item: MXA-0525
  • Ticket key: ISIS2-00723
  • Source references:
    • docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json
    • docs/domains/isis/remediation-v2/ISIS_V2_AUDIO_SFX_PACK_REQUIREMENTS_BRIEF.json
    • docs/domains/isis/remediation-v2/ISIS_V2_AUDIO_SFX_PACK_BASELINE_WORKFLOW_GRAPH.json
    • docs/domains/isis/remediation-v2/ISIS_V2_WORKFLOW_AUTHORING_GUIDE.json
    • libs/isis/workflows/src/workflows/audio/sfx-sound-designer.json
    • libs/isis/workflows/src/workflows/audio/music-cue-composer.json
    • libs/isis/workflows/src/workflows/audio/voice-performance-synthesis.json
    • docs/domains/isis/remediation-v2/ISIS_V2_AUDIO_CONDITIONING_SUPPORT.md
    • 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