Princess GRWM Makeup Story · öffentlicher Open Skill
Princess GRWM Makeup Story
Princess GRWM Makeup Story ist ein öffentlicher Open Skill auf Digen. Öffne ihn, um zu sehen, was dieser Workflow erstellt.
Beauty
2 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/640731/2026-09-25/qwkjtumn.jpg
# Princess "Get Ready With Me" — Magical Fairy Makeup Story ## When to use - The user wants a vertical (9:16) "Get Ready With Me" fairy-tale princess makeup video series: ~3 minutes, 18 scenes of 10s each, with dialogue + makeup sounds + actions, in premium 3D fairy-tale animation style. - The user wants to advance or change a single step: regenerate one scene, produce the next clip, restyle the character, or mix the episode. ## Reference files - `references/scene-script.md`: The full 18-scene script (title, product, action, dialogue, sounds). Read it before generating scenes. - `references/style-guide.md`: Character lock, product lock, and style conventions. Read before generating any image. ## Core locks (must hold in every scene) - **Character lock**: the same 18-year-old princess in every scene — emerald-green eyes, rosy cheeks, natural pink lips, long chestnut-brown wavy hair, pearl-and-crystal hair accessories. She wears a pastel-lavender satin robe during prep, then a gorgeous lavender princess gown. Face, hair, body proportions and voice stay 100% consistent. - **Product lock**: recognizable real luxury beauty brands with logos visible (Charlotte Tilbury Magic Cream, Estée Lauder Double Wear, NARS concealer, Fenty Match Stix, Rare Beauty blush, ABH Brow Wiz, Urban Decay palette, Dior mascara, Fenty Gloss Bomb, Charlotte Tilbury setting spray). - **Style**: original premium 3D fairy-tale animation, ultra-HD, luxurious enchanted princess bedroom, cute realistic makeup products, soft cinematic lighting, sparkling fairy particles. ## Steps 1. First use `write_todos` to list the stages (character → scene images → voiceover → scene videos → music → mix) and update it as you progress. 2. **Character lock**: if the user provided a character reference image, use it as the identity anchor (the preset `princess_ref` asset is the default). If none exists, generate one with `generate_image` (`model='t2i'`, `orientation='portrait'`) following the character lock in `references/style-guide.md`. `name='Princess Reference'`, `entity_type='characters'`. 3. **Scene images**: read `references/scene-script.md`. For each of the 18 scenes, generate a scene image with `generate_image` (`model='i2i'`, `orientation='portrait'`, `resolution='1080P'`), passing the character reference in `input_urls` to keep identity consistent. Prompt = scene location + product + action from the script, plus the style lock. `name='Scene N — <title>'`, `entity_type='storyboard_images'`. 4. **Voiceover**: for each scene, generate the princess's dialogue line with `generate_tts` (`model='tts.design'`, warm young-female fairy-tale voice, `voice_instruction` describing the princess voice). `name='VO Scene N'`, `entity_type='voiceovers'`. 5. **Scene videos**: for each scene image, generate a ~10s clip with `generate_video` (`model='i2v'`, `orientation='portrait'`, `duration=10`), passing the scene image as the start frame; describe the action + sounds from the script. `name='Clip N — <title>'`, `entity_type='storyboard_videos'`. 6. **Music**: generate a soft magical fairy-tale background track with `generate_music` (light orchestral + chimes, gentle, non-vocal). `name='GRWM Background Music'`, `entity_type='music'`. 7. **Mix**: stitch all 18 clips in order with `mix_clips` (`orientation='portrait'`), adding each scene's voiceover track and the background music; layer the makeup sound effects described in the script. `name='Princess GRWM — Full Episode'`, `entity_type='final_videos'`. 8. On success, reply in natural language (don't paste URLs), and call `set_guidance` to suggest next actions (e.g. regenerate a scene, restyle the character, mix the episode). ## Notes - Keep the character reference image as the identity anchor for every image/video step; never let a scene drift from the character lock. - Intermediate step-by-step products (scene images, clips, voiceovers) will be visible on the canvas alongside the final cut — that's expected. - Report failures honest