Witch Vampire Selfie Duo · skill pública Open Skill
Witch Vampire Selfie Duo
Witch Vampire Selfie Duo é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.
Roleplay
0 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321678/2026-10-22/bv5pdax8.webp
# Witch Vampire Selfie Duo Two of you, one Halloween frame. Your selfie splits into a glam witch with a glowing orb and a fanged vampire under a blood-red moon — same face, two spooky looks. ## When to use - The user wants their selfie turned into a Halloween two-panel portrait with both a glamorous witch and a vampire version of themselves (witch and vampire selfie, dual Halloween look, two-costume portrait) - A variation on a previous result: witch left Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult (any gender), face clear and front-facing, single subject only. Ask for another photo if the face is tiny, blurred, turned away or partly hidden | | Description | No | tuned default below | What the user wants; merged into the prompt | | Side | No | `vampire right` | witch left, vampire right (default), vampire left, witch right, or user-described | | Look | No | `both looks` | both looks (default), witch only, vampire only, or user-described | | Moon | No | `blood-red moon` | blood-red moon (default), pale silver moon, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16 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. - Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors. ## Steps 1. Read `references/image-edit.md` for prompt structure. 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. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Witch Vampire Selfie Duo', entity_type='skill_generation')`. Merge the user's details and options into the template. 4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely. 5. Reply in one or two sentences, e.g. "Your witch vampire selfie duo is ready. Want another take with witch left?" Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: a dramatic two-panel Halloween portrait of the same adult from the photo in two costume looks: a glamorous witch in a tall pointed hat with a jeweled brooch, lace-trimmed dark gown and a glowing purple crystal orb, and a vampire in a high-collared crimson-lined cape, dark red lips, subtle fangs and a garnet choker, arranged as <side: witch left, vampire right (default), vampire left, witch right, or user-described>, <look: both looks (default), witch only, vampire only, or user-described>, hair loose and glossy in both, hazy <moon: blood-red moon (default), pale silver moon, or user-described> and gnarled trees behind, carved pumpkins with candle glow and drifting embers in the foreground, moody rim light, rich blacks and violet-red accents, sharp beauty retouch, tasteful non-explicit adult Halloween costume photography. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text