Pattern chooser

Every tried-and-tested recipe in the engine, as a card. Filter by lane, stage, tier or capability to find the path for the work in front of you, then add the ones you want to your plan. Jump in at any stage; nothing here is a fixed order.

Lane
Stage
Tier
Capability
recondraftbuilt

Lyric analysis pass

Turn lyrics into themes, mood, story seed and 8-12 panel beats before any spend.

text-onlygate
Cost: - · Stage: analyse

Models: claude CLI or local Qwen

Inputs: A vault note at status ingested.

Outputs: Analysis merged into the note; status becomes analysed.

Risk: Cheap to redo. Read the story seed and beats and fix by hand.

recondraftdesigned

Recon draft clip

Fast image-to-video test on the cheapest tier; keep the good frames as LoRA training data.

batchharvest-lora-data
Cost: ≈A$0.03-0.10 per 6s clip · Stage: video

Models: HunyuanVideo 1.5

Inputs: A keyframe or panel plus a short motion prompt.

Outputs: A rough clip; salvaged stills feed the cast foundry.

Risk: Accept jank. Batch overnight on interruptible GPUs; cap spend per song.

recondraftdesigned

Model bake-off

Run the same shot across several models to see which wins on your own material.

batchevaluation
Cost: ≈A$0.10-0.30 per shot per model · Stage: video

Models: HunyuanVideo 1.5, Wan 2.2, LTX-2.3

Inputs: One fixed shot spec.

Outputs: A side-by-side sheet; the winner gets promoted for that use.

Risk: Only promote a new model to Hero after it beats the incumbent here.

reconheropremiumdesigned

Character LoRA foundry

Train a reusable LoRA for a hero recurring character; validate before it's allowed downstream.

char-loraone-offasset
Cost: ≈A$2-7 per character (30-60 min A100) · Stage: cast

Models: FLUX.1-dev or Qwen-Image base

Inputs: A curated reference set, ideally seeded from your own art and photos.

Outputs: A versioned .safetensors in the asset registry, with trigger word and sample grid.

Risk: A bad LoRA poisons every downstream job. Test-sheet it before use; version it.

reconheropremiumdesigned

Singer / band likeness LoRA

Same foundry, aimed at real people (singers, band, supports) for on-model performance shots.

char-loralikenessasset
Cost: ≈A$2-7 per person · Stage: cast

Models: FLUX.1-dev or Qwen-Image base

Inputs: Consented reference photos of the person.

Outputs: A versioned likeness LoRA in the registry.

Risk: Keep consent and any private likenesses local; mark the asset private.

reconreleasestandarddesigned

Reference-image character

Hold a character across shots with multi-reference, no training. Good for occasional cast.

char-refno-training
Cost: generation cost only · Stage: cast

Models: FLUX.2 multi-ref, Qwen-Image-Edit

Inputs: 1-10 reference images of the character.

Outputs: On-model frames without a trained LoRA.

Risk: Weaker lock than a LoRA under heavy motion; fine for lighter appearances.

reconreleaseherodraftdesigned

Comic pre-viz panels

Render 8-12 stills from the panel beats. The second cheap gate before any video spend.

stillscheap-gate
Cost: ≈A$0.01-0.05 per panel · Stage: panels

Models: Qwen-Image, FLUX.2 Klein

Inputs: A briefed note with panel beats and its cast.

Outputs: A panel set; status becomes panels. Approve the strongest.

Risk: Stills are cheap to re-roll; do the visual arguing here, not in video.

releaseherodraftplanned

Keyframe selection

Promote the approved panels to start and end frames for video shots.

selection
Cost: - · Stage: panels

Models: -

Inputs: Approved panels.

Outputs: Keyframe pairs that bookend each motion.

Risk: Pick pairs that imply believable motion between them.

releaseherostandarddesigned

Pose capture + retarget

Capture a move from any footage and retarget it onto your character.

pose-capturecontrol
Cost: capture is local and cheap; drive is video-gen cost · Stage: motion

Models: DWPose, AnimateAnyone/UniAnimate-class

Inputs: A reference clip (phone footage, a performance) plus a target character.

Outputs: A pose-driven clip of your character performing the move.

Risk: Capture and pose maps run local; only the driven render costs GPU.

releaseherostandarddesigned

Beat-synced motion

Snap a captured pose track to the song's beat grid so the movement lands on the music.

beat-synccontrol
Cost: - · Stage: motion

Models: librosa, Demucs

Inputs: A pose track and the song's audio.

Outputs: A beat-aligned motion track ready to drive generation.

Risk: Runs local on audio analysis; no GPU cost until render.

releaseherostandardplanned

Duplicate / mirror choreography

Apply one captured motion to several cast members, or mirror it, before rendering.

control
Cost: - · Stage: motion

Models: -

Inputs: A captured motion track and target cast.

Outputs: Group or symmetric choreography as data.

Risk: Pure data manipulation; free until it hits the generator.

heropremiumdesigned

Controlled hero shot

Pose, depth and reference conditioned video for a deliberately blocked hero shot.

controlcontinuity-lockpose-capture
Cost: ≈A$0.30-1.50 per shot · Stage: video

Models: Wan-VACE-class controllable video

Inputs: Keyframes, a pose or depth map, cast and location assets.

Outputs: A directed shot with intended blocking and continuity.

Risk: The most demanding path; prove the shot at draft before rendering premium.

releaseherostandarddesigned

Location plate + lock

Establish a consistent environment and reuse it across every shot in a scene.

continuity-lockasset
Cost: generation cost only · Stage: scene

Models: Qwen-Image, SAM 2

Inputs: A location description or plate image.

Outputs: A registered location asset shots can pull by name.

Risk: Lock it once; reuse buys both consistency and cheaper shots.

releaseherostandarddesigned

Object / prop transfer

Detect, lift and place a consistent object or prop across shots.

continuity-lockcontrol
Cost: generation cost only · Stage: scene

Models: SAM 2, Grounding DINO, inpaint

Inputs: A reference of the object and the target frames.

Outputs: The prop held consistent through the scene.

Risk: Detection and matting run local; only the placement render costs GPU.

releasestandardplanned

Beat-synced lyric montage

Cut approved clips to the beat and render for each platform. The forgiving, shareable lane.

beat-syncassemblemulti-platform
Cost: - · Stage: assemble

Models: librosa, ffmpeg

Inputs: Approved clips and the song audio.

Outputs: A cut, rendered at 9:16, 1:1 and 16:9.

Risk: Local assembly; the cheapest way to a publishable, community-shareable piece.

releaseheropremiumplanned

Vertical micro-drama cut

A short vertical story with dialogue voice and lip-sync, cut for phone-first viewing.

tts-lipsyncassemblevertical
Cost: voice + lipsync + assembly · Stage: assemble

Models: Qwen3-TTS, LatentSync/InfiniteTalk, ffmpeg

Inputs: A story seed, cast, and approved shots.

Outputs: A 9:16 micro-drama.

Risk: Lip-sync is a real gate; vet on a Recon pass first.

reconreleaseherodraftdesigned

TTS voiceover

Narration or spoken-word voiceover from a script. The non-music backbone.

voicenarrationnot-music
Cost: - · Stage: voice

Models: Qwen3-TTS, Kokoro-82M

Inputs: A script and a chosen voice.

Outputs: A voice track ready to cut against picture.

Risk: Runs light and local; Kokoro is CPU-viable for fast drafts.

reconherostandarddesigned

Voice clone (character / singer)

A cloned voice for a recurring character or singer, registered like a cast asset.

voicelikenessasset
Cost: - · Stage: voice

Models: Qwen3-TTS, Chatterbox v3

Inputs: A few seconds of consented reference audio.

Outputs: A reusable voice profile in the asset registry.

Risk: Keep consent and private voices local; mark the asset private.

reconreleaseherodraftdesigned

Speech-to-text transcribe

Transcribe dialogue or voiceover to timed text. Feeds captions, edits and search.

sttnot-musiccaptions-source
Cost: - · Stage: voice

Models: Whisper large v3, faster-whisper

Inputs: Any audio or video with speech.

Outputs: A timed transcript (word and segment timestamps).

Risk: Local and cheap; distil/faster variants run near realtime.

releaseherodraftdesigned

Auto captions / subtitles

Generate SRT from transcription and burn styled captions for phone-first viewing.

captionssttassemblemulti-platform
Cost: - · Stage: voice

Models: Whisper large v3, ffmpeg

Inputs: A clip with speech, or an existing transcript.

Outputs: An SRT and a caption-burned render.

Risk: Always proofread auto-captions before publish; names and lyrics trip them.

herostandardplanned

Cultural-translation dub

Transcribe, translate, re-voice and re-sync into another language. For the cultural-translation work.

voicestttranslationnot-music
Cost: voice + lipsync cost · Stage: voice

Models: Whisper large v3, Qwen3-TTS, LatentSync

Inputs: A finished clip and a target language.

Outputs: A dubbed, lip-synced version.

Risk: Translation needs a human check for meaning and register, not just literal words.