comfyui-prompt-engineer

Files (1)

• SKILL.md

SKILL.md (first lines)

# ComfyUI Prompt Engineer

> All recommendations in this skill are subordinate to `state/inventory.json`, `foundation/hardware-profile.md`, and current version constraints.

Generates optimized prompts tailored to specific models and identity methods. Different models respond differently to prompts.

## Model-Specific Prompt Rules

### FLUX.1 (dev/schnell/Kontext)

- **Style**: Natural language descriptions work best
- **CFG**: 3.5-4 (very low)
- **Quality tags**: Minimal - FLUX doesn't need "masterpiece, best quality"
- **Length**: Medium (50-100 words)
- **Structure**: `{subject description}, {setting}, {lighting}, {camera/style}`

**Good FLUX prompt:**
```
photorealistic portrait of a person with [hair description], [eye description], and
[distinctive facial features], wearing [wardrobe], sitting in [setting] with warm
ambient lighting, shallow depth of field, shot on Sony A7IV, 85mm lens
```

**Bad FLUX prompt (too many quality tags):**
```
masterpiece, best quality, 8k uhd, highly detailed, photorealistic portrait...
```

### SDXL (RealVisXL, Juggernaut, etc.)

- **Style**: Quality tags at front help significantly
- **CFG**: 7-9
- **Quality tags**: Include `masterpiece, best quality, photorealistic`
- **Length**: Medium-long (50-150 words)
- **Structure**: `{quality tags}, {trigger word}, {subject}, {details}, {setting}, {style}`
- **Weighted syntax**: Supported `(important:1.3)` or `((very important))`

**Good SDXL prompt:**
```
masterpiece, best quality, char_token, photorealistic portrait of a person,
detailed skin texture, [eye description], [hair description],
natural lighting from window, indoor setting, shallow depth of field,
RAW photo quality, 8k uhd, film grain
```

### SD 1.5

- **Style**: Tag-based works best
- **CFG**: 7-8
- **Quality tags**: Essential
- **Length**: Shorter (30-80 words)
- **Structure**: `{quality}, {trigger}, {subject}, {details}, {style tags}`

### Wan 2.2 Video (legacy 2.1 prompting is similar)

- **Style**: Concise motion descriptions
- **CFG**: 5-7
- **Quality tags**: Minimal
- **Length**: Short (20-50 words)
- **Focus**: Describe the motion, not just the appearance
- **Structure**: `{subject}, {action/motion}, {setting}, {quality}`

**Good Wan prompt:**
```
the character talking naturally with gentle hand gestures,
seated at a modern desk, soft studio lighting, high quality
```

### AnimateDiff

- **Style**: Same as base model (SD1.5/SDXL) but add motion keywords
- **Motion keywords**: Include camera/subject motion description
- **Length**: Same as base model

## With Identity Methods

### InstantID Prompts

**Key adjustments:**
- DO NOT describe specific facial features (the model provides them)
- DO describe everything else: clothing, pose, setting, lighting
- Keep CFG at 4-5

```
photorealistic portrait, wearing black leather jacket, standing in an alley,
dramatic side lighting, urban setting, moody atmosphere, 8k quality
```

### PuLID Prompts

**Key adjustments:**
- Can include some facial descriptions (PuLID is more tolerant)
- Method "neutral" for realistic, "fidelity" for exact match
- CFG 5-7

```
char_token, photorealistic portrait, eyes visible, natural styling,
professional headshot, neutral grey background, studio lighting
```

### IP-Adapter FaceID

**Key adjustments:**
- Describe the style you want, not the face
- weight_type "style transfer" for 3D→realistic
- Standard CFG for base model

```
photorealistic portrait, DSLR photo quality, natural skin texture,
warm indoor lighting, bokeh background, professional photography
```

### FLUX Kontext (Editing)

**Key adjustments:**
- Describe the EDIT, not the full image
- Be specific about what to change
- Mention what to preserve

From calebmills99/VUORSE-VORTEX, MIT.

More from calebmills99/VUORSE-VORTEX