# Art Consistency

> 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 delivery

- Skill: `ismael-joffroy-chandoutis/art-consistency` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ismael-joffroy-chandoutis/art-consistency`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ismael-joffroy-chandoutis/art-consistency/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ismael-joffroy-chandoutis (https://skillmd.com/u/ismael-joffroy-chandoutis)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/ismael-joffroy-chandoutis/art-consistency

---


# Art Consistency & Visual QA

## Triggers
- 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

## Patterns

### Character Bible First


Create a comprehensive character documentation before any generation


Starting work on a new character, beginning a series, or character lacks documentation


```
CHARACTER BIBLE: Luna Silverfall
================================

IDENTITY ANCHORS (use EXACT words every time):
- Face: "heart-shaped face, large violet eyes, small upturned nose"
- Hair: "silver twin-tails, waist-length, star-shaped hair clips"
- Body: "petite build, 155cm, slender frame"
- Outfit: "black sailor uniform with purple trim, knee-high boots"
- Accessories: "crescent moon pendant, fingerless black gloves"

STYLE DESCRIPTORS:
- Art Style: "2D anime, cel-shaded, clean linework, soft shadows"
- Color Palette: #7B68EE (violet), #C0C0C0 (silver), #000000, #FFD700
- Lighting: "soft anime lighting, subtle rim light"

PROMPT TEMPLATE:
"Luna Silverfall, heart-shaped face, large violet eyes, silver twin-tails
with star clips, black sailor uniform with purple trim, [ACTION], [SETTING],
2D anime style, cel-shaded, soft anime lighting"

REFERENCE IMAGES: [turnaround sheet link]
```

### Turnaround Sheet Generation


Generate multi-view reference sheet before any other images


New character without references, or existing character needs standardization


```
TURNAROUND SHEET PROMPT:
"character design sheet, multiple views, front view, side view,
back view, 3/4 view, [CHARACTER DESCRIPTION],
white background, consistent lighting, reference sheet layout,
same character all views, anime style"

OUTPUT: 4-6 views showing character from different angles
USE: As reference for all future generations of this character
```

### Pre-Generation Validation


Check all consistency requirements before generating


Every single generation - no exceptions


```
PRE-GENERATION CHECKLIST:
[ ] Character bible exists and is loaded
[ ] Prompt includes ALL identity anchors (exact wording)
[ ] Style descriptors match series aesthetic
[ ] Reference image available (turnaround or previous approved image)
[ ] Color palette specified or implied in prompt
[ ] Seed locked if continuing from previous generation
[ ] Model appropriate for style (Flux for realism, etc.)

If ANY checkbox is unchecked → FIX BEFORE GENERATING
```

### Post-Generation QA


Rigorous visual comparison against references before approval


After every generation, before showing to user or using in production


```
POST-GENERATION QA CHECKLIST:

FACE VERIFICATION:
[ ] Eye color matches reference
[ ] Eye shape matches reference
[ ] Face shape matches reference
[ ] Nose shape matches reference
[ ] Expression appropriate for scene

HAIR VERIFICATION:
[ ] Color exact match (check in different lighting)
[ ] Style matches (twintails are twintails, not ponytail)
[ ] Length consistent
[ ] Accessories present (hair clips, ribbons, etc.)

OUTFIT VERIFICATION:
[ ] All clothing items present
[ ] Colors match reference
[ ] Details preserved (trim, patterns, buttons)
[ ] Accessories present (jewelry, gloves, etc.)

BODY/PROPORTIONS:
[ ] Height/build consistent with character
[ ] Proportions match (head-to-body ratio)
[ ] Pose anatomically sound

STYLE VERIFICATION:
[ ] Art style matches series (anime vs realistic vs cartoon)
[ ] Line weight consistent
[ ] Shading style matches
[ ] Color saturation appropriate

QUALITY CHECKS:
[ ] No artifacts or glitches
[ ] Hands rendered correctly (count fingers!)
[ ] No floating elements or disconnected parts
[ ] Background appropriate and not distracting

VERDICT: [ ] APPROVED  [ ] REGENERATE (note issues)
```

### Seed Locking for Series


Lock generation seed when making variations of same scene


Creating multiple versions, iterating on a scene, or continuation shots


```
SEED MANAGEMENT:

1. First generation: Let seed be random, note it if result is good
2. Variations: Keep SAME seed, change only ONE element
   - Same seed + different expression = consistent character, new emotion
   - Same seed + different pose = risky, may cause drift

RULE: Change the smallest thing first
- Expression only? Keep seed
- New pose? May need new seed, regenerate until consistent
- New outfit? Major change, expect inconsistency, multiple attempts

NEVER change seed + prompt + model + settings simultaneously
```

### Style Reference Anchoring


Use reference images to lock in visual style across generations


Working on a series, maintaining consistent aesthetic, or matching existing art


```
STYLE REFERENCE METHODS:

1. IP-Adapter: Upload reference → generates with similar style
   - Good for: Pose, composition, overall vibe
   - Set control strength: 0.6-0.8 for style, 0.3-0.5 for loose inspiration

2. LoRA/Kontext: Train on 4-8 character images
   - Good for: Character identity across many generations
   - Trigger word: "[character_name]" in every prompt

3. Style Reference URL (Midjourney): --sref [image_url]
   - Good for: Art style consistency
   - Style weight: 100 default, 50-150 range

4. Image-to-Image: Start from approved image
   - Good for: Variations on existing scene
   - Strength: 0.3-0.5 to keep most of original
```

### Progressive Disclosure for Complex Characters


Build character consistency gradually through staged generation


Complex character design, or establishing new character identity


```
STAGED CHARACTER ESTABLISHMENT:

Stage 1: Face/Portrait (5-10 generations)
- Generate close-up portraits until face is consistent
- Lock in exact facial feature descriptions
- Create "golden reference" portrait

Stage 2: Full Body (5-10 generations)
- Use Stage 1 face as reference
- Establish body proportions
- Lock in outfit details

Stage 3: Turnaround Sheet
- Generate multi-view sheet using Stage 1+2 references
- Verify consistency across all angles

Stage 4: Action Poses
- Only after Stages 1-3 are locked
- Use turnaround as reference
- QA each generation against sheet

DO NOT skip stages. Rushing causes compounding drift.
```

## Anti-Patterns

### Generate and Hope

**Why:** Generating images without reference or documentation and hoping they match

### Vague Prompts

**Why:** Using non-specific descriptors like "pretty girl" or "anime style"

### Synonym Substitution

**Why:** Using different words for the same feature across prompts

### Skipping QA

**Why:** Approving generated images without systematic review

### Close Enough Thinking

**Why:** Accepting images with minor inconsistencies because regenerating takes time

### Reference-Free Continuation

**Why:** Generating new images of established character without loading references

### Multi-Variable Changes

**Why:** Changing multiple things at once (pose + outfit + background + lighting)

### Trust Previous Success

**Why:** Assuming a prompt that worked before will work identically again

## Validation Checklist

- [ERROR] **Generation Without Character Bible**
  - Attempting to generate character without a character bible. Consistency impossible.
  - Fix: Create character bible FIRST with:
- Identity anchors (face, hair, body, outfit, accessories)
- Style descriptors (art style, color palette, lighting)
- Prompt template with exact wording
- Reference images (turnaround sheet if possible)

- [ERROR] **Generation Without Reference Image**
  - Generating established character without reference image. Drift guaranteed.
  - Fix: Load reference image before generation:
- Upload turnaround sheet or approved previous image
- Use IP-Adapter or image-to-image with reference
- Or use trained LoRA with trigger word

- [WARNING] **Vague Identity Descriptors**
  - Prompt uses vague identity descriptors. Will produce inconsistent results.
  - Fix: Replace vague descriptors with SPECIFIC identity anchors:
BAD: "pretty anime girl with blue hair"
GOOD: "heart-shaped face, large sapphire blue eyes, small nose,
       sky blue twin-tails shoulder-length with ribbon clips"

- [WARNING] **Vague Style Descriptors**
  - Prompt uses vague style descriptors. Art style will drift between generations.
  - Fix: Specify EXACT style characteristics:
BAD: "anime style"
GOOD: "90s anime cel-shading, bold black outlines,
       hard shadows, saturated colors, Studio Ghibli influence"

- [WARNING] **Color Without Specification**
  - Color mentioned without specific shade. Colors will vary between generations.
  - Fix: Use specific color descriptors or hex codes in documentation:
BAD: "blue eyes"
GOOD: "deep sapphire blue eyes" or "eyes #1E90FF"

Document exact color in character bible for reference.

- [WARNING] **Synonym Usage Across Prompts**
  - Different words for same feature detected. Pick ONE term and use consistently.
  - Fix: Document canonical term in character bible.
Use ONLY that term in all prompts.
Never substitute synonyms.

- [ERROR] **Facial Feature Drift**
  - Facial features do not match reference. Character identity compromised.
  - Fix: Do NOT approve. Regenerate with:
- Stronger reference image influence (increase IP-Adapter strength)
- More specific facial feature description in prompt
- Different seed if pattern persists

- [ERROR] **Hair Style/Color Drift**
  - Hair does not match reference. Visible consistency break.
  - Fix: Do NOT approve. Regenerate with:
- Explicit hair description in prompt
- Hair color in specific terms (not just "blue")
- Accessories explicitly mentioned

- [ERROR] **Outfit/Clothing Drift**
  - Outfit does not match reference. Character consistency broken.
  - Fix: Do NOT approve. Regenerate with:
- Complete outfit description in prompt
- Each accessory explicitly mentioned
- Color specifications for each item

- [WARNING] **Art Style Drift**
  - Art style drifting from series aesthetic.
  - Fix: Compare to series reference images.
If drift detected:
- Reinforce style descriptors in prompt
- Use style reference image
- Consider different model if style incompatible

- [ERROR] **Quality Issues**
  - Quality issues detected. Cannot approve for delivery.
  - Fix: Do NOT approve. Either:
- Regenerate with different seed
- Use inpainting to fix specific issues
- Adjust prompt if issue is systematic

- [WARNING] **Cross-Image Consistency Check**
  - Inconsistency detected across series images.
  - Fix: Review all series images together.
Identify the drift point.
Regenerate divergent images with stronger reference.
Consider retraining LoRA if drift is systematic.

- [WARNING] **Multi-Character Scene Consistency**
  - Multi-character scene has consistency issues.
  - Fix: For multi-character scenes:
- Generate characters separately if possible
- Use composite/layering approach
- Verify each character against their bible
- Check relative proportions against size chart


## Handoffs

- **generate image|create image|make image** → `ai-image-generation` — Image generation needed - ensure consistency validation wraps the generation
- **generate video|create video|animate** → `ai-video-generation` — Video generation needed - ensure consistency validation for each keyframe
- **brand guide|brand identity|logo** → `branding` — Brand-level consistency needed, not character-level
- **ui components|interface design** → `ui-design` — UI consistency needed, hand off visual standards
- **creative direction|campaign|content strategy** → `ai-creative-director` — Strategic creative direction needed beyond visual consistency

