How to Create an AI Influencer
Offers practical workflows for AI filmmakers needing consistent UGC-style digital avatars, including exact credit costs and a crucial camera framing tip to reduce facial distortion.
What this lesson covers
Diego Galvao demonstrates how to design a custom digital influencer character sheet and animate it using reference footage inside Higgsfield's Genjutsu feature. He also explains how to re-prompt character outfits in the image tab while maintaining consistent framing.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 01:31 ↗
Setting specific physical parameters like build, age, and character type in the AI Influencer dashboard produces reusable two-panel character sheets.
- 03:23 ↗
Generating a Genjutsu motion video costs 66 credits at 1080p resolution versus 42 credits when generated at 720p.
- 04:41 ↗
Keeping reference character sheets in a landscape 16:9 aspect ratio provides an optimal base for re-prompting costumes before generating vertical 9:16 final outputs.
- 07:17 ↗
Recording reference footage with the camera close to the subject's face significantly reduces generation artifacts such as mouth warping.
Workflow outlined in the video
- Navigate to the Genjutsu section on Higgsfield and open the 'Create your influencer' dashboard.
- Configure attributes such as character type, gender, build, hairstyle, and ethnicity to generate a two-panel character sheet.
- Take the character reference into the Image tab, select a model like Cream 5.0 Pro at 16:9, and prompt wardrobe modifications while preserving character identity.
- Return to Genjutsu, upload the modified character reference sheet, and attach a mobile or downloaded reference video.
- Select output resolution (720p or 1080p) to balance visual fidelity against credit consumption, then render the motion transfer.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
243 views captured 13 October 2026. ReelStack recommendation score: 32/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.74× views vs 5 other channel videos observed at a similar age. View-evidence factor 20% (views / (views + 1,000))
- 25% freshness: 85/100 with a 14-day half-life
- 20% momentum: 60 views/day vs 77 channel baseline (4 comparable uploads), with the same view-evidence factor
- 10% engagement: 49/100; likes + 4× comments, smoothed with a 500-view neutral prior