Media

Marketing visuals — ads, og images, social cards, hero shots, promo reels — are generated through Higgsfield AI instead of commissioned per asset. The /higgs skill wraps the CLI in a zero-question playbook: it picks the model, aspect ratio, and style from pre-made tables, prices the job before spending, and downloads the result. Finished media feeds the Social Hub, which stages the post for human approval before any channel sees it.

The doctrine

Model defaults

Costs are per job, re-verified 2026-07-27 with higgsfield generate cost.

Naming trap: nano_banana_flash is Nano Banana 2; nano_banana_pro is Nano Banana Pro. There is no nano_banana_2 job type — that ID was retired and now errors. Only the seedance family accepts --video-references.

Workflow

Copyhiggsfield account status                            # preflight — re-auth only if this fails
node scripts/higgs-library.mjs lookup \
  --prompt "..." --model z_image --ratio 16:9        # free — already own it?
higgsfield generate cost z_image --prompt "..."      # free estimate
higgsfield generate create z_image --prompt "..." --aspect_ratio 16:9 --wait --json
higgsfield generate create kling3_0_turbo --prompt "..." --start-image <winner> --wait --json

generate has exactly six subcommands — cost, create, get, list, wait, workflow. Every job goes through create; there is no generate image or generate video.

Results are JSON arrays carrying result_url; outputs land in ~/Downloads/higgs/ as YYYY-MM-DD-<slug>.<ext>.

Asset library

Every paid job is fingerprinted by (prompt, model, ratio, resolution) in content/media/library.json and mirrored to object storage, so the same shot is never bought twice and assets survive a cleared Downloads folder.

Copynode scripts/higgs-library.mjs lookup --prompt "..." --model M --ratio 16:9
node scripts/higgs-library.mjs add <file> --prompt "..." --model M --brand hogwarts --credits 1
node scripts/higgs-library.mjs import    # register whatever is already on disk
node scripts/higgs-library.mjs push      # mirror to the serving origin
node scripts/higgs-library.mjs stats     # assets, credits spent, credits saved

Prompts are normalized before hashing, so trivial rewording still hits; a different ratio or model is correctly a miss. /social --media consults the library before spending a credit.

Setup

1. Install the higgsfield CLI (aliases higgs, hf).
2. higgsfield auth login — browser OAuth, completes hands-free.
3. higgsfield workspace set <workspace-id> — required after every re-auth.
4. Brand kit and web product IDs are pinned in the skill so output stays on-brand.

Credentials live in the Keychain, never in a repo — see Credentials.

Known limits

• The balance is 0.7 credits (2026-07-27). Only z_image drafts still run; every final image, hero, and video is unaffordable until the workspace is topped up. Free-plan credits look like a one-time grant, not a monthly refill.
• The Plus trial requires a working card — currently blocked by the Mada rejection.
• The Higgsfield MCP endpoint is registered but unauthenticated; the CLI is the primary lane.
• cdn.databayt.org returns 403 for every key in the bucket — a CloudFront fault that predates the library. Assets are served from the S3 origin until it is fixed; the library re-links in place with push --base once it is.
• Video is entirely untested — no clip has ever been generated.
• Arabic creative still needs manual typography in post.

Related

• Social Automation — where generated media gets published
• Brand & Voice — the rules every visual obeys
• Credentials — where the Higgsfield session lives