Gymnastics Pose Restyle · Open Skill 公開技能
Gymnastics Pose Restyle
Late-night city lights, so I wanted a quick way to try a cleaner athletic pose. I like that it keeps the same face while rebuilding the body in a gymnastics or fitness stance. **tips from me:** - use an adult full-body or three-quarter photo so the limbs have room to move - try the default arabesque balance, or pick handstand prep, bridge stretch, or athletic lunge - the default ratio is 3:4, with 2:3 and 9:16 available on request - add a description when you want a specific pose post what you make, I like seeing the results.
Sports
2 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-17/8s2bhkbb.webp
# Gymnastics Pose Restyle Same face, new pose. Your photo is reposed into a clean athletic gymnastics or fitness stance with natural proportions and photoreal detail. ## When to use - The user wants the person in their photo repositioned into an athletic gymnastics or fitness pose while keeping the same face (gymnastics pose editor, fitness pose restyle, athletic body pose still) - A variation on a previous result: handstand prep Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult, ideally full-body or three-quarter so limbs can be reposed. Ask for another photo if the person is tiny or heavily cropped | | Description | No | tuned default below | What the user wants; merged into the prompt | | Pose | No | `arabesque balance` | arabesque balance (default), handstand prep, bridge stretch, athletic lunge, 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='Gymnastics Pose Restyle', 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 gymnastics pose restyle. I can also try handstand prep 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 person repositioned into <pose: a clean gymnastics scale or arabesque balance (default), a handstand prep, a flexible bridge stretch, a strong athletic lunge, or user-described>, identity and facial features preserved exactly, natural body proportions and anatomically correct limb placement, consistent lighting perspective and texture with a clean gym or bright studio backdrop, photoreal full-body result, fully clothed in athletic wear that fits the pose. <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 sentence; retry once only if transient; never invent links. - The face changes: regenerate once with the identity clause first; then say so honestly. ## Examples **Default**: the user says "use this pic" with a photo. Use pose `arabesque balance`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your