Artistic Silhouette Keep · عوامی Open Skill
Artistic Silhouette Keep
hook: I turn an adult photo into a bold graphic silhouette, keeping selected details visible. tips: Send a clear adult photo. I convert the subject into a silhouette poster, with face and hair detailed by default. Tip: Keep the face in frame / Tip: Use 1:1 or 9:16 for a poster grid.
Other
0 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284953/2026-10-19/3q5qyj6s.webp
# Artistic Silhouette Keep Bold silhouette, chosen details kept. Your photo becomes a graphic art silhouette — hair, face or props can stay rendered while the rest drops to clean shape. ## When to use - The user wants a photo turned into a graphic silhouette while selected parts stay detailed (artistic silhouette conversion, selective silhouette poster, high-contrast keep-detail silhouette) - A variation on a previous result: only the eyes Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult, face clear. Ask for another photo if the face is tiny, blurred or hidden | | Subject photo | No | — | the adult whose silhouette is built; face clear | | Description | No | tuned default below | What the user wants; merged into the prompt | | Keep detailed | No | `the face and hair` | the face and hair (default), only the eyes, a held prop, or user-described | | Ink | No | `matte black` | matte black (default), deep indigo, warm sepia, or user-described | | Ground | No | `flat cream paper` | flat cream paper (default), deep charcoal, soft pastel wash, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 1:1, 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='Artistic Silhouette Keep', 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. "All set. Your artistic silhouette keep is on the canvas. Next I can do only the eyes." 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 subject converted into a graphic artistic silhouette on a <ground: flat cream paper (default), deep charcoal, soft pastel wash, or user-described>: the body reads as a crisp solid silhouette in <ink: matte black (default), deep indigo, warm sepia, or user-described> while <keep: the face and hair stay detailed (default), only the eyes stay detailed, a held prop stays detailed, or user-described parts stay detailed>; clean high-contrast edges, poster-art feel, fully clothed opaque outfit, no logos or readable text. <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 unless requested. ``` Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style. ## Failure handling - `success=false`: say what failed in one