Pp Wavespeed

WaveSpeed — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the wavespeed-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install wavespeed --cli-only

2. Verify: wavespeed-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/ai/wavespeed/cmd/wavespeed-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

WaveSpeed hosts image, video, audio, and 3D models behind one API. This CLI adds a dynamic model runner for slash-delimited model IDs, free price estimates, local file uploads, a generation library with cost reports, and a D2C content layer (plan, pack, batch, variants, compose, aspects, restyle, brand, qa). Paid submissions are never replayed, and every post-submit failure keeps the prediction ID and a recovery command.

When to Use This CLI

Use this CLI to generate or edit images and video with WaveSpeed models from scripts or agents: check prices, upload reference files, run models with waits and downloads, and keep a local record of every generation and its cost. Use the plan/pack/batch commands for multi-platform D2C content production.

Anti-triggers

Do not use this CLI for:

• Training or fine-tuning models
• Hosting or serving your own models

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Core

• run — Submit WaveSpeed model runs with prompt shorthand, typed --set inputs, local @file media uploads, price estimates, waiting, recovery-safe downloads, and library recording.

  Use it for any single generation; the prediction ID and recovery command survive every post-submit failure.

  wavespeed-pp-cli run --model-id google/nano-banana-2/edit --prompt "a red mug on oak" --images @ref.png --set aspect_ratio=9:16 --wait --download 'out/mug_{index}.{ext}' --agent

• schema — Fetch the live WaveSpeed model catalog and print the request schema for a model or project alias.

  Check accepted inputs and enums before a paid run.

  wavespeed-pp-cli schema google/nano-banana-2/edit --agent

• price — Estimate WaveSpeed model pricing with the same input syntax used by run, without submitting a prediction.

  Free; quote the cost before spending.

  wavespeed-pp-cli price --model-id google/nano-banana-2/edit --set aspect_ratio=9:16 --set resolution=2k --agent

• aliases — Read wavespeed.json aliases, default model, and output directory settings for repeatable local workflows.

  See which short names map to which models.

  wavespeed-pp-cli aliases --agent

• init — Write a starter wavespeed.json with aliases, default model, and output directory.

  Start a new image project.

  wavespeed-pp-cli init

Media

• upload — Upload local image, video, or audio files to WaveSpeed media storage for use as model input URLs, retrying stalled uploads with a size-scaled deadline.

  Turn a local file into a URL a model accepts.

  wavespeed-pp-cli upload ./ref.png --agent

• download — Download generated output URLs with directory, exact-path, or templated-path destinations, never sending API credentials to CDN hosts.

  Re-fetch outputs from a finished prediction.

  wavespeed-pp-cli download "$OUTPUT_URL" --output 'out/{index}.{ext}'

• last — Print or open the most recent downloaded output.

  Grab the path of the last generated file.

  wavespeed-pp-cli last

Plan

• plan brief-to-shotlist — Turn a free-text brief into a structured shotlist across platforms and aspect ratios with a hybrid deterministic-parser/LLM planner.

  Draft the shot list for a campaign.

  wavespeed-pp-cli plan brief-to-shotlist --prompt "Helm Black launch" --platforms instagram,tiktok --agent

• plan model-pick — Recommend a model for an intent from the live catalog with rationale.

  Choose a model for a job.

  wavespeed-pp-cli plan model-pick "short product video" --agent

• plan cost-estimate — Price a shotlist against live /model/pricing and the account balance, with cached-pricing fallback and per-shot breakdown.

  Check a shotlist fits the budget.

  wavespeed-pp-cli plan cost-estimate shotlist.json --agent

• qa preflight — Pass/warn/fail validation of a shotlist: balance vs cost, model availability, prompt safety, platform request-shape, and brand coverage.

  Gate a pack before producing it.

  wavespeed-pp-cli qa preflight shotlist.json --agent

Produce

• pack — Produce a multi-platform creative pack from one concept at stable packs/<slug>/<platform>/ paths with per-platform manifests, concurrency, cost ceiling, and image-dimension validation; a rerun archives the superseded manifest.

  Produce platform-ready assets.

  wavespeed-pp-cli pack --concept "Helm Black hero" --platforms instagram,tiktok --max-cost 5.00 --agent

• batch — Submit many prompts from CSV or JSON with a spend ceiling and fail-fast/fail-tolerant semantics; records completed generations before any abort.

  Run a prompt list under a budget.

  wavespeed-pp-cli batch --from prompts.csv --max-cost 5.00 --agent

• variants — Sweep seed, style, or model off a base shot to produce comparable outputs with side-by-side metadata.

  Explore seeds or models for one shot.

  wavespeed-pp-cli variants --base shotlist.json --vary seed --count 4 --agent

• compose — Run an explicit multi-step pipeline (text->image->upscale->video), feeding each step's output to the next, with rollback of later steps on failure.

  Turn a prompt into an image and then a clip.

  wavespeed-pp-cli compose --steps "text->image,image->video" --prompt "..." --models m1,m2 --agent

Refine

• aspects — Re-frame one image into standard platform aspect ratios, using outpaint when supported and an anchored re-render otherwise.

  Make 9:16 and 1:1 versions of a hero image.

  wavespeed-pp-cli aspects hero.png --platforms instagram,tiktok --agent

• restyle — Apply a brand profile or explicit style to an existing asset via img2img with a style prompt.

  Bring an asset onto brand.

  wavespeed-pp-cli restyle hero.png --brand helm --agent

Library

• library — List, search (FTS5), show, tag, export, and cost-report the local generation library by brand, model, platform, and tag.

  Find a past generation or total spend.

  wavespeed-pp-cli library cost-report --group-by model --agent

• brand — Create, inspect, apply, and edit brand profiles that auto-merge into pack, compose, variants, restyle, and run.

  Set up a brand for consistent output.

  wavespeed-pp-cli brand init helm --palette '#111,#eee' --voice calm

Command Reference

account_balance — Manage account balance

• wavespeed-pp-cli account-balance — Retrieve the authenticated account balance.

billings — Billing and usage records

• wavespeed-pp-cli billings — Search billing records for the authenticated account.

media_uploads — Manage media uploads

• wavespeed-pp-cli media-uploads — Upload one existing local media file (image, video or audio) to WaveSpeed storage and return its URL for model inputs.

model_pricing — Manage model pricing

• wavespeed-pp-cli model-pricing — Estimate the unit price for a model run using the same inputs that will be submitted to the model endpoint.

models — Model catalog and model metadata

• wavespeed-pp-cli models — List available WaveSpeed models and their API schemas.

prediction_deletions — Manage prediction deletions

• wavespeed-pp-cli prediction-deletions — Delete one or more predictions from history.

prediction_results — Manage prediction results

• wavespeed-pp-cli prediction-results <task_id> — Retrieve the latest status and result payload for a prediction task.

predictions — Prediction submission history and result retrieval

• wavespeed-pp-cli predictions — Query recent prediction history. The API history window is limited; sync accumulates across runs.

usage_stats — Manage usage stats

• wavespeed-pp-cli usage-stats — Retrieve usage statistics for the authenticated account.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

wavespeed-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Recipes

Image edit with a reference, 9:16 at 2k

wavespeed-pp-cli run --model-id google/nano-banana-2/edit --prompt "$PROMPT" --images https://wavespeed.ai/anchor.png --set aspect_ratio=9:16 --set resolution=2k --wait --download 'raw/shot_{index}.{ext}' --record --agent

Pass a URL or a local @file; local files upload automatically. The download template names each output.

First-and-last-frame video

wavespeed-pp-cli run --model-id bytedance/seedance-v1.5-pro/image-to-video --prompt "$MOTION" --image https://wavespeed.ai/a.jpg --last-image https://wavespeed.ai/b.jpg --set duration=5 --wait --wait-timeout 10m --download 'clip_{index}.{ext}' --record --agent

--wait-timeout bounds polling; on timeout the prediction ID and recovery command are printed.

Spend for a session

wavespeed-pp-cli billings --page-size 20 --agent

Billing rows carry the charged price per prediction.

Plan a campaign

wavespeed-pp-cli plan brief-to-shotlist --prompt "launch" --platforms instagram,tiktok --agent

Save the shotlist, then run plan cost-estimate and qa preflight on it before pack.

Auth Setup

WaveSpeed uses an API key sent as Authorization: Bearer <key>. Create one at https://wavespeed.ai/accesskey and export it as WAVESPEED_API_KEY. doctor verifies the key with a free /balance read.

Run wavespeed-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

• --json — one JSON document on stdout (sync progress events go to stderr)

• --compact — keep identity/status/timestamp fields; does not change the document vs stream shape

• --csv / --plain — tabular rows (collection envelopes unwrap to the row array)

• --quiet — one identity value per row, no envelope

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  wavespeed-pp-cli billings --agent --select code,data,message

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

• Explicit confirmation — --agent does not imply --yes; pass --yes separately only after the target, arguments, and side effects are clear

• Explicit retries — use --idempotent only when an already-existing create should count as success

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set WAVESPEED_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: WAVESPEED_CONFIG_DIR, WAVESPEED_DATA_DIR, WAVESPEED_STATE_DIR, WAVESPEED_CACHE_DIR.

• Resolution order is per-kind env var, --home, WAVESPEED_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.

• Run wavespeed-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  {
    "mcpServers": {
      "wavespeed": {
        "command": "wavespeed-pp-mcp",
        "env": {
          "WAVESPEED_HOME": "/srv/wavespeed"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use WAVESPEED_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing WAVESPEED_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
wavespeed-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "wavespeed-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `wavespeed-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; wavespeed-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.