Video Call Outfit Reveal · öffentlicher Open Skill
Video Call Outfit Reveal
When the beat drop hits at the crosswalk, I’m already thinking about a quick outfit reveal. I like that an adult photo becomes a phone call clip, with the outfit changing on camera. **tips from me:** - use an adult photo with your face clear and unobstructed - try the default tailored black blazer and mini skirt, or pick the streetwear set - choose a 6 s or 10 s clip, with 9:16 portrait as the default orientation - add a description for your own look, but keep the wardrobe fully covering Post what you make, I want to see your outfit reveal.
TryOn
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-17/8pmcafj3.gif
# Video Call Outfit Reveal Phone propped up, call connected: "Put on that outfit." Your photo becomes a video-call clip where the casual look transforms into a sharp new outfit right on camera. ## When to use - The user wants to become this look in a video: a playful video-call style clip where the person in their photo answers a request and their outfit transforms into a new look on camera - A variant on a previous result (another style, length or orientation) Not for: Still images only, or animating a picture with no transformation. ## 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 | | Description | No | tuned default below | What the user wants; merged into the prompt | | Outfit | No | `tailored black blazer and mini skirt` | tailored black blazer and mini skirt (default), cream knit dress, satin evening dress, streetwear set, or user-described | | Duration | No | `6 s` | 6 s (default), or 10 s | | Orientation | No | `9:16` portrait | Other ratios 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. - Video does not allow NSFW content: keep wardrobe fully covering and refuse sexual requests. Suggestive fashion looks stay as still images. ## Steps 1. Read `references/transformation-reveal.md` before writing prompts. 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. **Before frame**: `generate_image(prompt=<BEFORE>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Video Call Outfit Reveal before', entity_type='work_in_progress')`: the person in their own clothes, already in the final scene, so both frames share the set. 4. **After frame**: `generate_image(prompt=<AFTER>, input_urls=[before frame, photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Video Call Outfit Reveal after', entity_type='work_in_progress')`: the hero key art. 5. **Self-check, one retry per frame**: if the face no longer reads as the same person, regenerate with the identity clause first and fewer face effects; if the after frame looks like mild makeup, regenerate with a bolder silhouette and stronger costume change. 6. **Reveal video**: `generate_video(prompt=<MOTION>, input_urls=[before frame, after frame], model='fl2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Video Call Outfit Reveal', entity_type='final_videos')`. If `fl2v` fails, fall back to `generate_video(prompt=<MOTION_I2V>, input_urls=[before frame], model='i2v', ...)`. 7. Reply in one or two sentences, e.g. "Done! Here's your video call outfit reveal. I can also try cream knit dress if you like." Results appear on the canvas; never paste URLs. ## Prompt templates **BEFORE** ```text The same adult from the reference: <identity line>. Keep their real face, hair and everyday outfit exactly. They stand in the final scene of this concept: the same adult sits on a black leather sofa in a dim modern living room framed like a front-camera video call; their casual knit sweater and lounge pants transform on camera into <outfit: a tailored black blazer over a silk blouse with a black mini skirt, opaque tights and pointed heels (default), or the user's described outfit>, they stand, smooth the jacket and settle back onto the sofa with a confident smile toward the screen; soft lamp light, cool blue window light, tasteful fashion styling, fully clothed and non-explicit, but before any change, wearing their own clothes, calm expression toward camera. Medium-full shot, eye-level, cinematic photoreal still, no text or lettering anywhere. ``` **AFTER** ```text The same adult from th