Workspace Structure
Each influencer lives in a dedicated folder:
~/influencers/
├── {persona-slug}/
│ ├── identity.md # Name, niche, voice, personality
│ ├── reference/ # Base images for consistency
│ │ ├── face-ref-1.png
│ │ └── style-guide.md
│ ├── content/
│ │ ├── photos/ # Generated images by date
│ │ └── videos/ # Generated videos by date
│ ├── captions.md # Caption templates, hashtags
│ ├── schedule.md # Posting schedule
│ └── analytics.md # Performance tracking
└── tools.md # Configured generation tools
Quick Reference
| Task |
Load |
| Create new persona (identity, niche, aesthetics) |
persona.md |
| Generate consistent photos |
image-gen.md |
| Generate videos (talking head, lifestyle) |
video-gen.md |
| Voice and audio (TTS, voice cloning) |
voice.md |
| Content strategy and captions |
content.md |
| Platform optimization (IG, TikTok, YT) |
platforms.md |
| Monetization (brand deals, affiliates) |
monetization.md |
| Legal and disclosure requirements |
compliance.md |
Persona Creation Checklist
Before generating any content:
Character Consistency Rules
Maintaining the same face/body across all content is CRITICAL.
For photos:
- Generate base reference set first (5-10 images, multiple angles)
- Use IP-Adapter or InstantID for every generation
- Same seed + similar prompt structure = more consistency
- Quality check EVERY image before posting
For videos:
- Use face-swap on real footage OR
- Generate with character LoRA if trained OR
- Talking head tools (HeyGen, D-ID) with reference image
Content Generation Flow
- Plan — Check schedule.md for what's needed today
- Generate — Use appropriate tool (see image-gen.md or video-gen.md)
- Review — Verify character consistency, quality
- Caption — Write engaging copy matching persona voice
- Schedule — Queue for optimal posting time
- Track — Log in analytics.md after posting
Common Patterns
| User says |
Agent does |
| "Create new influencer" |
Run persona creation flow, set up workspace |
| "Generate photos for today" |
Check schedule, generate with consistency refs |
| "Make a TikTok video" |
Generate 9:16 video with talking head or lifestyle footage |
| "Write captions for these" |
Draft captions matching persona voice + niche hashtags |
| "How is she performing?" |
Summarize analytics.md, suggest improvements |
| "Add brand deal content" |
Generate sponsored content with disclosure |
Tool Configuration
Store active tools in ~/influencers/tools.md:
## Active Tools
- Image: Nano Banana Pro (Gemini)
- Video: Kling / Runway
- Voice: ElevenLabs (voice_id: xxx)
- Lip Sync: HeyGen
Update when switching providers. All generation scripts read from here.
1---2name: influencer3description: Create, manage, and scale AI-generated virtual influencers with consistent characters, multi-platform content, and monetization workflows.4---56## Workspace Structure78Each influencer lives in a dedicated folder:9```10~/influencers/11├── {persona-slug}/12│ ├── identity.md # Name, niche, voice, personality13│ ├── reference/ # Base images for consistency14│ │ ├── face-ref-1.png15│ │ └── style-guide.md16│ ├── content/17│ │ ├── photos/ # Generated images by date18│ │ └── videos/ # Generated videos by date19│ ├── captions.md # Caption templates, hashtags20│ ├── schedule.md # Posting schedule21│ └── analytics.md # Performance tracking22└── tools.md # Configured generation tools23```2425---2627## Quick Reference2829| Task | Load |30|------|------|31| Create new persona (identity, niche, aesthetics) | `persona.md` |32| Generate consistent photos | `image-gen.md` |33| Generate videos (talking head, lifestyle) | `video-gen.md` |34| Voice and audio (TTS, voice cloning) | `voice.md` |35| Content strategy and captions | `content.md` |36| Platform optimization (IG, TikTok, YT) | `platforms.md` |37| Monetization (brand deals, affiliates) | `monetization.md` |38| Legal and disclosure requirements | `compliance.md` |3940---4142## Persona Creation Checklist4344Before generating any content:45- [ ] Define niche (fitness, lifestyle, tech, fashion, etc.)46- [ ] Create identity document (name, age, location, backstory)47- [ ] Generate 5-10 reference images for face consistency48- [ ] Define visual style (lighting, colors, settings)49- [ ] Create voice profile (if using TTS/videos)50- [ ] Draft personality guidelines for captions5152---5354## Character Consistency Rules5556Maintaining the same face/body across all content is CRITICAL.5758**For photos:**591. Generate base reference set first (5-10 images, multiple angles)602. Use IP-Adapter or InstantID for every generation613. Same seed + similar prompt structure = more consistency624. Quality check EVERY image before posting6364**For videos:**651. Use face-swap on real footage OR662. Generate with character LoRA if trained OR673. Talking head tools (HeyGen, D-ID) with reference image6869---7071## Content Generation Flow72731. **Plan** — Check schedule.md for what's needed today742. **Generate** — Use appropriate tool (see image-gen.md or video-gen.md)753. **Review** — Verify character consistency, quality764. **Caption** — Write engaging copy matching persona voice775. **Schedule** — Queue for optimal posting time786. **Track** — Log in analytics.md after posting7980---8182## Common Patterns8384| User says | Agent does |85|-----------|------------|86| "Create new influencer" | Run persona creation flow, set up workspace |87| "Generate photos for today" | Check schedule, generate with consistency refs |88| "Make a TikTok video" | Generate 9:16 video with talking head or lifestyle footage |89| "Write captions for these" | Draft captions matching persona voice + niche hashtags |90| "How is she performing?" | Summarize analytics.md, suggest improvements |91| "Add brand deal content" | Generate sponsored content with disclosure |9293---9495## Tool Configuration9697Store active tools in `~/influencers/tools.md`:9899```markdown100## Active Tools101- Image: Nano Banana Pro (Gemini)102- Video: Kling / Runway103- Voice: ElevenLabs (voice_id: xxx)104- Lip Sync: HeyGen105```106107Update when switching providers. All generation scripts read from here.
dvcrn