This tutorial climbs the next rung: keeping one character looking like the same person across multiple shots. We start with why drift happens (a video generator is stateless, so it re-derives a plausible face on every call) and the "second-clip identity drift" wall, documented as almost never random.
Then the four anchors, weakest to strongest:
- Character sheets built in an image model: turnaround, expression set, neutral lighting, plain background, one full-height shot (Higgsfield Soul ID guide). Tools include Nano Banana Pro, FLUX.2 Pro, Seedream 4.5, and Ideogram Character.
- Single reference / start frame (image-to-video), plus no-training adapters PuLID and IPAdapter (LoRA vs references). Runway Gen-4 reportedly hits 95%+ from one reference.
- Native multi-reference, the episode's thesis: Runway Gen-4 References, Veo 3.1 Ingredients to Video, Kling Elements, Seedance 2.0 Omni Reference, and Midjourney Omni-Reference.
- Trained character LoRA on fal.ai or Replicate: roughly fifteen to thirty varied images, two to five dollars a run, base-model lock-in.
Decision rule: default to multi-reference; train a LoRA only for high-volume, exact-lock, stable-base work. Plus pitfalls (outfit drift, lighting, identity bleed, reference quality), provenance (SynthID and C2PA, the EU AI Act and SB 942), real-person rights (NO FAKES Act), and benching it yourself on the Video Arena leaderboard.