Skip to main content
Platform

02 / 05 · Forge

Best-of-three on every hero shot.

For each hero asset we fire three models in parallel. The judge layer (next page) picks the winner. You only see the survivor — but the rejected attempts stay in the lineage so we can train the LoRA on what passed.

Multi-model

Why ensembles beat single-model pipelines

Every model has a failure mode. Flux is great at lighting; sometimes loses fine product detail. Recraft is great at composition; sometimes mangles text. Ideogram is great at text; sometimes flatter lighting. Running all three on the same brief and letting the judge pick lifts hero-shot accept rate from ~40% to ~75% on our benchmarks.

Brand LoRA

Per-workspace, compounding moat

Every workspace gets its own LoRA, trained on your reference photos via Vertex AI Custom Training. Vertex re-trains automatically every 50 approvals, which means a six-month-old workspace produces measurably better outputs than a brand-new one.

On top of LoRA: IP-Adapter / Redux pinning lets you anchor a specific reference photo for outputs that need to match a specific lookbook frame.

The stack

What's actually firing

Asset kindModelsWhere
Image — heroFlux 1.1 Pro Ultra · Recraft V3 · Ideogram 3.0fal.ai · Replicate
Image — batchFlux Schnell · Recraft V3 fastRunPod self-hosted A100
Video — heroVeo 3 · Kling 2.6 Pro · Runway Gen-4Vertex AI · fal.ai
Video — batchWan 2.2 5B · Wan 2.2 A14BRunPod self-hosted A100
Talking headHeyGen Rachel · Hedra Character-3HeyGen · Hedra
Voice cloneElevenLabs Pro v2 (per-brand)ElevenLabs

Cost discipline

Spend caps, not surprise bills

Daily and per-run spend caps configured in Secret Manager, enforced before the first inference call. If your team's running a campaign and crosses the cap, the dispatcher pauses and pings the workspace owner — no $5K Friday-night bills.

~$0.08
Per hero image (cap-enforced average)
~$2.40
Per 30s talking-head video
$200/mo
Default daily-cap envelope, configurable
0
Surprise overages on shipped workspaces