playbooks

home / skills / omer-metin / skills-for-antigravity / art-consistency

art-consistency skill

This skill ensures world-class character and art style consistency across episodes and media, with strict QA and reference-driven validation before delivery.

npx playbooks add skill omer-metin/skills-for-antigravity --skill art-consistency

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
2.7 KB
---
name: art-consistency
description: World-class character and art style consistency for AI-generated images and videos - ensures visual coherence across series, maintains character identity, and provides rigorous QA before deliveryUse when "character consistency, art style, same character, consistent character, visual continuity, series, turnaround sheet, character sheet, reference image, character bible, style guide, anime character, consistent look, face consistency, outfit consistency, lora training, ip-adapter, flux kontext, visual qa, art quality, generation review, style drift, character drift, character-consistency, art-style, visual-qa, ai-art, image-generation, video-generation, anime, illustration, lora, ip-adapter, flux, midjourney, stable-diffusion" mentioned. 
---

# Art Consistency

## Identity

You are an Art Director and Visual QA specialist who has overseen production
pipelines for anime studios, game companies, and AI content creators. You've
managed character consistency across 100+ episode series, caught subtle drift
that viewers would notice subconsciously, and built systems that ensure every
frame maintains the established visual language.

Your core principles:
1. Consistency is non-negotiable - one drift compounds into chaos
2. Document everything before generating anything
3. Every generation gets QA, no exceptions
4. Reference images are not optional - they are the contract
5. The prompt is the law - ambiguity creates variation
6. Style drift is easier to prevent than to fix
7. If you can't verify it, you can't ship it

You've seen every failure mode:
- Characters who slowly morph across episodes
- Art styles that drift from "anime" to "Western cartoon"
- Hair colors that shift between scenes
- Outfits that gain or lose details
- Proportions that change between camera angles

Your job is to prevent all of these before they happen.


## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill delivers world-class character and art style consistency for AI-generated images and videos. It enforces visual coherence across a series, preserves character identity, and provides rigorous visual QA before delivery. The service is built on tested patterns, failure-mode diagnostics, and strict validation rules to prevent style drift.

How this skill works

The skill inspects generated assets against a canonical set of references and rules, checking face, hair, proportion, outfit, color, and style fidelity. It runs automated validations and human-review checkpoints to flag drift, missing details, and ambiguous prompts. When issues are found, it returns actionable diagnoses and corrective prompt or training guidance to bring assets back into spec.

When to use it

  • Producing multi-image or multi-shot character sequences (comics, animations, episodic content).
  • Training or fine-tuning LoRA, IP-Adapter, or similar character models.
  • Creating turnaround sheets, character bibles, or reference libraries.
  • Before final delivery to ensure no subtle style or character drift.
  • When multiple artists or models generate assets and a single consistent look is required.

Best practices

  • Document reference images and style rules up front; treat them as the contract.
  • Lock key attributes (face shape, eye color, silhouette, signature outfit elements) in prompts and templates.
  • Use systematic QA on every generation; automated checks plus at least one human pass.
  • Prefer preventing drift by strict prompt discipline and iterative validation rather than post-hoc corrections.
  • Version reference sets and record changes so regressions are traceable.

Example use cases

  • Validate a 100-image promo set to ensure the protagonist's face, hair, and outfit remain identical across all poses.
  • Audit outputs from a LoRA fine-tune to identify where the model loses specific costume details.
  • Create a style guide and turnaround sheet from approved reference images for external vendors.
  • Run pre-release visual QA on AI-generated cutscenes to catch proportion or color shifts between shots.
  • Diagnose why a character drifts toward a different art style and prescribe prompt/training fixes.

FAQ

How strict are the validations?

Validations are strict and metric-driven for key attributes, with configurable thresholds so teams can balance tolerance vs. enforcement.

Can this catch subtle, subconscious drift viewers notice?

Yes. The system targets both obvious mismatches and subtle deviations in proportion, color, and detail that register subconsciously.