Pearl Diver Costume Portrait · öffentlicher Open Skill
Pearl Diver Costume Portrait
Pearl Diver Costume Portrait ist ein öffentlicher Open Skill auf Digen. Öffne ihn, um zu sehen, was dieser Workflow erstellt.
TryOn
1 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284957/2026-10-19/6z529ut6.webp
# Pearl Diver Costume Portrait White cotton, seaworn rope, salt air. The woman in your photo becomes a traditional free-diver in a historical diving costume — same face, same hair, same art style. ## When to use - The user wants the woman in their photo restyled as a traditional free-diver in a historical diving costume (pearl diver outfit, ama diver look, traditional diving costume portrait) - A variation on a previous result: indigo wrap tunic Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult woman, face clear; three-quarter or full body preferred so the costume can read. Ask for another image if the face is tiny or the body is mostly cropped out | | Description | No | tuned default below | What the user wants; merged into the prompt | | Outfit | No | `white cotton top with sash` | white cotton top with sash (default), indigo wrap tunic, or user-described | | Setting | No | `wooden boat deck` | wooden boat deck (default), rocky shore with nets, 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='Pearl Diver Costume Portrait', 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. "Done! Here's your pearl diver costume portrait. I can also try indigo wrap tunic if you like." 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: the same adult woman (keep her face, hairstyle, body shape and the source art style exactly) dressed as a traditional free-diver in <outfit: white cotton short-sleeve top and wrapped work trousers bound with a wide sash (default), indigo-dyed wrap tunic with rope belt, or user-described>: a snug cloth head wrap over her hair, a rope belt with a small wooden float and diving weights, barefoot on <setting: weathered wooden boat deck with calm sea behind (default), sunlit rocky shore with fishing nets, or user-described>, sea-salt sheen on her skin, warm coastal daylight, fully clothed and tasteful, heritage documentary photography feel. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested. ``` Quality bar: Make the new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that