comfyui-character-gen

The saved excerpt is a snapshot from when this skill was listed. The external source remains the complete and most current version.

---
name: comfyui-character-gen
description: Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
---

# ComfyUI Character Generation Expert

Build production-ready ComfyUI workflows for consistent character generation across image, video, and voice modalities.

## Quick Decision: Which Approach?

**Starting from reference images (like 3D renders)?**
→ **InfiniteYou** (state-of-the-art 2025) or InstantID + IP-Adapter (proven, lower VRAM)

**Need highest identity fidelity?**
→ **FLUX.2** (NEW 2026: up to 10 ref images) or **PuLID Flux II** (no model pollution)

**Want iterative editing without retraining?**
→ **FLUX Kontext** (context-aware, maintains consistency across edits)

**Creating video content?**
→ **LTX-2** (NEW 2026: 4K production-ready), **Wan 2.2 MoE** (film-level), or **FramePack** (60-sec on 6GB!)

**Need voice for character?**
→ **TTS Audio Suite** (unified platform, 23 languages) or **F5-TTS Cross-Lingual** (NEW 2026)

## Core Workflow Patterns

### Pattern 1: Zero-Shot Character Generation (No Training)

Best for: Quick iteration, 3D-to-photorealism conversion, limited reference images

```
Load Reference Face → InstantID + IP-Adapter FaceID → ControlNet Pose → KSampler → FaceDetailer → Upscale
```

**Critical settings:**
- CFG: 4-5 (prevents burning with InstantID)
- Resolution: 1016×1016 (avoids watermark artifacts)
- IP-Adapter weight: 0.6-0.8
- InstantID noise injection: 35% to negative

See `references/workflows.md` for complete node configurations.

### Pattern 2: LoRA + Identity Methods (Maximum Consistency)

Best for: Production work, character series, video generation base

```
Train LoRA → Load LoRA + Checkpoint → Add InstantID/PuLID → Generate → FaceDetailer → ReActor (optional) → Upscale
```

**Training requirements:**
- 15-30 images, varied poses/expressions/lighting
- Unique trigger word (e.g., "sage_character")
- See `references/lora-training.md` for full parameters

### Pattern 3: Video Generation Pipeline

Best for: Talking heads, character animation, promotional content

```
Generate/Load Hero Image → Wan 2.1 I2V OR AnimateDiff → FaceDetailer per frame → Frame Interpolation → Video Combine
```

**Model selection:**
- Wan 2.1 14B: Best quality, 24GB+ VRAM, slower
- Wan 2.1 1.3B: 8GB VRAM, good quality, faster
- AnimateDiff Lightning: Fastest, best for iteration

### Pattern 4: Talking Head with Voice

Best for: Character dialogue, presentations, social content

**Two approaches available:**

```
Approach 1 (Image → Talking Head):
Character Portrait → Generate Audio → SadTalker/LivePortrait → CodeFormer Enhancement → Final Video

Approach 2 (Video → Add Voice):
Existing Video → Generate Audio → Wav2Lip Lip-Sync → CodeFormer Enhancement → Final Video
```

See `references/talking-head-workflows.md` for complete workflows and `references/voice-synthesis.md` for voice creation options.

## Model Recommendations (2026 Updated)

### Image Generation
| Use Case | Model | Notes |
|----------|-------|-------|
| Best photorealism | FLUX.1-dev | Slow but superior quality |
| Multi-reference consistency | **FLUX.2** | **NEW 2026**: Up to 10 ref images, strong identity preservation |
| Fast iteration | RealVisXL V5.0 | Good balance speed/quality |
| Character editing | **FLUX Kontext** | Context-aware, maintains consistency across edits |
| Iterative