Image Factory

Plugin marketplaces

This plugin belongs to AIGC content creation.

Category	Marketplace	Purpose
Full-stack development	Full Stack Plugins	Architecture and UI design, code understanding, quality checks, code review, workflow governance, and server operations
AIGC content creation	Full AIGC Plugins	Image, video, audio, music, 3D, and multimodal content creation

Turn a reference-driven image task into an auditable production run: a validated plan, an approved spend, and a hash-verified receipt for every artifact.

English | 简体中文 · Install · Quick start · Skills · Troubleshooting

Positioning

image-factory produces verifiable image batches. It turns references and a visual direction into a validated plan, quotes the batch, waits for your approval, generates one image per plan item through the host's image tool, and records a recomputed hash, size, and dimension receipt for every file.

The plugin exposes two layers. In Codex the built-in imagegen / image_gen path is preferred and needs no provider key. The unchanged Baoyu workflows are offered only after an explicitly observed image-quota exhaustion in Codex, or on a host without a verified native image capability. The Factory loop adds the governed batch: plan validation, approval, receipts, evaluation, and recovery.

Property	Value
Plugin ID	image-factory
Version	0.9.1+codex.20261018
Maturity	No production-readiness claim; the newest runtime record covers the 0.8.0 candidate
Runtime	Python 3.11+, standard library only
MCP server	None; the manifest declares no MCP entry

0.8.0 added multi-hash evidence, stratified calibration, a review workspace, and a runtime acceptance matrix. The paid 4/8/12, cross-host, and fault-injection cases remain NOT_RUN; synthetic tests do not establish live character, prop, or style stability.

Installation

Prerequisites

• Python 3.11 or newer on PATH.
• The Codex CLI reachable on PATH, or CODEX_HOME pointing at an installation.
• Factory-only batches need no API key and no npm package.
• The Baoyu fallback requires bun or npx plus whatever credential the selected provider documents; the codex-cli provider reuses an already signed-in Codex CLI.

From the plugin marketplace

codex plugin marketplace add partme-ai/full-aigc-plugins
codex plugin add image-factory@full-aigc-plugins

From the repository-local marketplace

codex plugin marketplace add full-aigc-plugins/image-factory-plugin --ref v0.9.1
codex plugin add image-factory@partme-ai-image-factory

Restart Codex or the ChatGPT desktop app and open a new task so the skills load.

For development, clone the repository and run bin/image-factory probe; it prints a JSON capability report for Python, the Codex CLI, and ledger access and never prints a secret value. codex plugin list should show image-factory@partme-ai-image-factory installed, enabled.

Quick start

1. Find an attributed prompt direction offline:

bin/image-factory prompt-search 'storybook illustration' --limit 3 --json

2. Write a batch plan, then validate and quote it. Validation rejects unknown fields, cap violations, and duplicate idempotency keys before anything is spent:

bin/image-factory validate-plan image-plan.json
bin/image-factory quote image-plan.json

3. Approve the exact plan hash and run:

bin/image-factory run image-plan.json --approval image-approval.json

4. Evaluate or reconcile an interrupted run:

bin/image-factory evaluate image-plan.json
bin/image-factory recover image-plan.json

Each attempt is a fresh streaming subprocess against the built-in image tool. There is no retry loop: a silent retry is how one bad prompt becomes a large bill. A failed item is terminal; optimize produces a new prompt round that needs its own approval.

What you can build

Workflow	Built-in path	Verifiable output
Find a direction	prompt-search over bundled templates	Ranked prompt directions with source attribution
Produce a governed batch	validate-plan → quote → run	Per-artifact hash, size, and dimension receipts
Keep a series consistent	consistency_profile, entity traits, role-aware references	Effective prompt and reference count reported by quote
Evaluate and iterate	evaluate + image-factory-review	Deterministic gate results, advisory dimension scores, next-round plan
Recover an interrupted run	recover	Reconciled ledger without another generation call
Make one ad-hoc image	Codex built-in imagegen	A bitmap asset outside the Factory ledger

Multi-image stories declare consistency_profile; anchors are injected into every selected frame in a fixed order and story_state compiles locks and transitions into the effective prompt. Anchors improve control but cannot guarantee model-level identity.

Skills

Skill	Purpose
image-factory-use	Picks the entry point for a batch request and never performs the work itself
image-factory-run	Validates, quotes, obtains approval, generates one image per item, and collects receipts
image-factory-judge	Runs deterministic gates, records advisory scores beside human labels, and writes the next round
image-factory-review	Writes the independent dimensioned advisory document consumed by evaluate and optimize
image-factory-recover	Reads the ledger and maps an interrupted or unknown batch to the single legal next step
image-factory-harness	Chooses Codex imagegen first, Baoyu only after quota evidence, and normalizes delivery evidence
imagegen	Managed snapshot of the Codex raster-image generation and editing instructions
baoyu-image-gen	Vendored multi-provider image generation through bun or npx
baoyu-cover-image	Vendored article-cover generation across aspect ratios
baoyu-xhs-images	Vendored social image-card series generation

The three Baoyu skills come from baoyu-skills v2.5.2, while imagegen and image-factory-use/run/judge/recover come from image-factory-skills v1.1.0; both sets are pinned in skills.lock.json. image-factory-harness and image-factory-review are plugin-local. Edit none of these copies in place.

Slash commands

Command	What it does
/image-factory	Total entry point; routes to run, judge, or recover
/image-factory-run	Quotes, approves, generates, and collects receipts for a batch
/image-factory-judge	Evaluates a finished batch and drives prompt optimization
/image-factory-recover	Restores an interrupted batch from the job ledger

Configuration

Setting	Where it lives	Notes
Codex home	CODEX_HOME environment variable	Defaults to the standard Codex location
Job ledger	The --job path, or <plan>.job.json	Plain JSON written atomically
Receipts	<job>.receipts/	One JSON file per artifact
Job lock	<job>.lock	Cross-process advisory lock
Credentials	None	The plugin stores no secret and the ledger rejects credential-like keys
Baoyu provider	Local environment or provider config	Chosen by the user, never written by the plugin

Exit codes are 0 success, 1 failure, 2 usage error, 3 approval required, 4 capability unavailable, 5 job locked, and 6 recovery required.

Architecture and security

flowchart LR
    A[References + direction] --> B[Prompt search]
    B --> C{Validate + quote}
    C -->|invalid| B
    C -->|valid| D{Approval}
    D -->|approved| E[Codex image tool]
    E --> F[Receipts + ledger]
    F --> G{Evaluate}
    G -->|failures| H[Optimize → new approval]
    G -->|none| I[Accepted batch]

Component	Owns	Does not own
bin/image-factory	CLI entry point	Business rules
scripts/plan_validator.py	Closed plan schema, caps, idempotency keys	Prompt quality
scripts/generation_runner.py	One fresh subprocess per attempt	Retry policy
scripts/job_ledger.py, scripts/receipt_store.py	Durable state, scrubbing, per-artifact re-verification	Remote lifetime
skills/ (10)	Routing, governance, and review instructions	Runtime enforcement

Authentication is Codex's own. The Factory path never calls an external generation API, never updates an upstream dependency on its own, and never writes a credential: the ledger rejects credential-like keys before writing anything. Reference inputs are validated before use, and every hash, size, and dimension is recomputed from disk with a second check that catches a file rewritten mid-validation.

Troubleshooting

Symptom	Check first	Resolution
probe reports the Codex CLI missing	PATH or CODEX_HOME	Point CODEX_HOME at the installation or fix PATH
Plan validation fails	The plan schema	Fix the named field; unknown fields are rejected on purpose
The run refuses to start	The approval file	Quote the plan again and approve the new revision
A run stops mid-batch	Ledger state	Run recover; verified receipts are reconciled, not regenerated
Hash verification fails	The artifact on disk	Treat it as a hard failure: the file changed after generation
The image quota is exhausted	Codex quota evidence	Only then choose a Baoyu fallback and configure its provider locally
Generation runs on Linux or Windows	Platform support	The generation path is verified on macOS only; elsewhere it stays NOT_RUN
A model name is missing from receipts	Platform boundary	The model is chosen by Codex; receipts record only what Codex reports

Upgrade

codex plugin marketplace upgrade partme-ai-image-factory
codex plugin add image-factory@partme-ai-image-factory

Contributing and support

Open functional issues at https://github.com/full-aigc-plugins/image-factory-plugin/issues. Before proposing a change, state the Python version you verified on, whether it alters the plan schema or the ledger format, and include the affected gates.

License

Apache-2.0 — see LICENSE, NOTICE, and THIRD_PARTY_NOTICES.md. Vendored Baoyu skills and the imagegen snapshot keep their upstream terms.