media-forgemf-examples-jalisted

# media-forge:mf-examples-ja Use Japanese examples as native prompt patterns, not translated English templates. The craft (subject, action, camera, light, sound, constraint) generalizes across providers; the reference tags in the worked examples below (`@Image1`, `@Video1`, `@Audio1`) are **Seedance-specific** reference-fusion syntax — preserve them exactly when the example targets Seedance, and see `[skill:mf-video-prompt]` for how they bind. For Kling or Higgsfield, adapt the same craft language to that provider's own reference mechanism (`kling-prompting`, `higgsfield-prompting`). ## Intent Japanese examples should feel like production notes a Japanese creator could actually use: polite where helpful, compact where the model needs clarity, and concrete enough that every emotion becomes framing, light, motion, sound, or post-production handling. ## Example Labels | Label | Meaning | |---|---| | `safe` | Original concept, no protected identity. | | `needs-owned-reference` | Requires user-owned, licensed, public-domain, or authorized asset. | | `provider-specific` | Depends on the active video/API provider. | | `rewrite-required` | Mentions protected identity, brand, celebrity, exact scene, song, or voice. | ## Safe Example Patterns **Product I2V:** `@Image1を商品参照として使い、ロゴ、ラベル、形状、色を正確に維持する。変化は小さな水滴が表面を下へ流れる動きと、左から横切る柔らかい暖色光だけ。Camera: locked product close-up, slow push-in. Sound: quiet room tone, one small glass tick at the end.` **Portrait micro-performance:** `@Image1の