Two Panel Style Swap · सार्वजनिक Open Skill
Two Panel Style Swap
Two Panel Style Swap Digen पर एक सार्वजनिक Open Skill है। खोलें और जानें कि यह वर्कफ़्लो क्या बनाता है।
TryOn
0 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321710/2026-10-21/aebg7u3g.webp
# Two Panel Style Swap Two looks, one frame. Your portrait is redrawn as a clean illustrated character on the left, while the illustrated character beside you steps out as a real adult cosplayer on the right, each keeping their own hair, colors and outfit. ## When to use - The user wants a two-panel swap between their own portrait and an illustrated character (photo-to-drawing swap, character-to-cosplayer match, two-panel art swap, OC made real) - A variation on a previous result: soft cel-shaded anime Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo of person 1 | Yes | — | Clear face, adult | | Photo of person 2 | Yes | — | Clear face, adult | | Description | No | tuned default below | What the user wants; merged into the prompt | | Style | No | `modern comic illustration` | modern comic illustration (default), soft cel-shaded anime, painterly storybook, or user-described | | Accent | No | `warm gold` | warm gold (default), navy, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 1:1, 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**: run `recognize_image` on each photo with the identity prompt (one compact line each). 3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo 1, photo 2], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Two Panel Style Swap', 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 two panel style swap. I can also try soft cel-shaded anime if you like." Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text Person 1: <identity 1>. Person 2: <identity 2>. Each keeps their own face. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: a fixed two-panel comparison split by a slim divider: left panel, the same adult from the portrait redrawn as a clean lined <style: modern comic illustration (default), soft cel-shaded anime, painterly storybook, or user-described> portrait; right panel, the same adult character from the illustration rendered as a photoreal adult cosplayer, one subject per panel, each keeping its own hairstyle, hair color, clothing and signature accessories, <pose: relaxed standing three-quarter (default), confident hand-in-pocket, or user-described>, clean seamless studio backdrop with soft even light, left panel edged in <accent: warm gold (default), navy, or user-described>, both adults fully clothed in modest costumes, tasteful. <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 suits the outfit (not the selfie background). ## Failure handling - `success=false`: s