Skeleton Gothic Beauty · compétence Open Skill
Skeleton Gothic Beauty
## <span style="color:#C77DFF">Cast</span> The shelf was tidy. The request was not. - I use one adult photo with a clear, front-facing face - Head-and-shoulders to half-body framing works - If the face is tiny, blurred, turned away, or covered, I ask for another ## <span style="color:#C77DFF">Result</span> - I create a vertical gothic beauty clip - Sugar-skull face paint - A dark corset-style gown - A moonlit castle courtyard ## <span style="color:#C77DFF">Details</span> - Gown: crimson-and-black velvet by default, plus black lace or deep purple brocade - Accent: blood-red eye shadow with crackle veins, violet and silver, or black-and-white - Backdrop: moonlit gothic castle courtyard, candlelit cathedral aisle, or misty graveyard gate - Duration: 6 or 10 seconds - Orientation: 9:16 portrait by default
Roleplay
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-20/djr8v6vh.webp
# Skeleton Gothic Beauty From an everyday selfie to a gothic Halloween queen: sugar-skull face paint, a dark corset-style gown and a moonlit castle courtyard, in one smooth vertical clip. ## When to use - The user wants to become this look in a video: a Halloween video where the person in their photo transforms into a skeletal gothic beauty - A variant on a previous result (another style, length or orientation) Not for: Still images only, or animating a picture with no transformation. ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult, face clear and front-facing, head-and-shoulders to half body. Ask for another photo if the face is tiny, blurred, turned away or covered | | Description | No | tuned default below | What the user wants; merged into the prompt | | Accent | No | `blood-red eye shadow with crackle veins` | blood-red eye shadow with crackle veins (default), violet and silver, black-and-white, or user-described | | Gown | No | `crimson-and-black velvet` | crimson-and-black velvet (default), black lace, deep purple brocade, or user-described | | Backdrop | No | `moonlit gothic castle courtyard` | moonlit gothic castle courtyard (default), candlelit cathedral aisle, misty graveyard gate, or user-described | | Duration | No | `6 s` | 6 s (default), or 10 s | | Orientation | No | `9:16` portrait | Other ratios on request | - If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use. - Video does not allow NSFW content: keep wardrobe fully covering and refuse sexual requests. Suggestive fashion looks stay as still images. ## Steps 1. Read `references/transformation-reveal.md` before writing prompts. 2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`. 3. **Before frame**: `generate_image(prompt=<BEFORE>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Skeleton Gothic Beauty before', entity_type='work_in_progress')`: the person in their own clothes, already in the final scene, so both frames share the set. 4. **After frame**: `generate_image(prompt=<AFTER>, input_urls=[before frame, photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Skeleton Gothic Beauty after', entity_type='work_in_progress')`: the hero key art. 5. **Self-check, one retry per frame**: if the face no longer reads as the same person, regenerate with the identity clause first and fewer face effects; if the after frame looks like mild makeup, regenerate with a bolder silhouette and stronger costume change. 6. **Reveal video**: `generate_video(prompt=<MOTION>, input_urls=[before frame, after frame], model='fl2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Skeleton Gothic Beauty', entity_type='final_videos')`. If `fl2v` fails, fall back to `generate_video(prompt=<MOTION_I2V>, input_urls=[before frame], model='i2v', ...)`. 7. Reply in one or two sentences, e.g. "All set. Your skeleton gothic beauty is on the canvas. Next I can do violet and silver." Results appear on the canvas; never paste URLs. ## Prompt templates **BEFORE** ```text The same adult from the reference: <identity line>. Keep their real face, hair and everyday outfit exactly. They stand in the final scene of this concept: the same adult transforms from their everyday photo into a skeletal gothic Halloween beauty: crisp skull face paint over their own features (white base, black nose and stitched-teeth mouth, <accent: blood-red eye shadow with crackle veins (default), violet and silver, all black-and-white, or user-described>), a long-sleeve high-neck <gown: crimson-and-black velvet gothic gown (default), black lace gothic gown, deep purple brocade gown, or user-describe