Mirror Double Costume Reveal · skill Open Skill công khai
Mirror Double Costume Reveal
Mirror Double Costume Reveal là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.
Meme
1 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321704/2026-10-20/b8gy5wyc.gif
# Mirror Double Costume Reveal You stay exactly as you are. Your reflection doesn't. In the glass, a witch hat and plum cape appear, tiny pumpkin lanterns glow, and the two of you react to each other in one seamless fixed-camera prank. ## When to use - The user wants to become this look in a video: a playful clip where only the reflection in the mirror puts on a Halloween costume while the real person stays unchanged - 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 photographed beside a clear mirror with the reflection visible, face and reflection both sharp. Ask for another photo if the mirror is angled away, fogged, cluttered or the face is tiny | | Description | No | tuned default below | What the user wants; merged into the prompt | | Costume | No | `purple witch hat and plum cape` | purple witch hat and plum cape (default), pointed hat with starry robe, jack-o'-lantern headpiece with dark cloak, or user-described | | Reaction | No | `surprised smile and step back` | surprised smile and step back (default), slow turn to the mirror, startled gasp, or user-described | | Duration | No | `6 s` | 6 s (default), or 10 s | | Orientation | No | `3:4` 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='3:4', name='Mirror Double Costume 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='3:4', name='Mirror Double Costume 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='3:4', duration=<d>, name='Mirror Double Costume 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. "All set. Your mirror double costume reveal is on the canvas. Next I can do pointed hat with starry robe." 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 standing beside a tall clear mirror, fully clothed in their original outfit, while only the reflection transforms into <costume: purple witch hat and plum cape (default), pointed hat with starry robe, jack-o'-lantern headpiece with dark cloak, or user-described> with its own independent expression; tiny glowing pumpkin lanterns drift in the mirror world, the real person reacts with a surprised smile and a