Two Photo Embrace Duo · Open Skill 公開技能
Two Photo Embrace Duo
Two Photo Embrace Duo 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。
Film
3 1 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284957/2026-10-21/ycpgjdyf.gif
# Two Photo Embrace Duo Two photos, one warm meeting. Both adults are lifted out of their own shots and placed into a single, softly lit moment where the embrace finally happens — heads tilt close, arms settle, breath calm. ## When to use - The user wants two people from separate photos brought together in one affectionate clip (two-photo hug video, put us in a scene together, couple embrace from two pics) - Another take with a different length or orientation Not for: Still images only. ## 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 | | Scene | No | `golden-hour rooftop terrace with warm sky glow` | golden-hour rooftop terrace with warm sky glow (default), nighttime train interior with blue bench seating, sunlit garden path, or user-described setting | | Pose | No | `standing embrace with a forehead touch` | standing embrace with a forehead touch (default), seated embrace with one leaning in, a lift-spin reunion, or user-described | | Duration | No | `6 s` | 6 s (default), or 10 s | | Orientation | No | `9:16 portrait` | 9:16 portrait (default), or 3:4, 1:1, 16:9 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/video-motion.md`. 2. **Identity read**: `recognize_image` on each photo (one compact identity line each). 3. **Keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo 1, photo 2], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Two Photo Embrace Duo keyframe', entity_type='work_in_progress')`. If the face drifts, regenerate once. 4. **Video**: `generate_video(prompt=<MOTION>, input_urls=[keyframe], model='i2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Two Photo Embrace Duo', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "Done! Here's your two photo embrace duo. I can also try sunlit garden path if you like." Results appear on the canvas; never paste URLs. ## Prompt templates **KEYFRAME** ```text Person 1: <identity 1>. Person 2: <identity 2>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Opening frame of this scene: two adult subjects (both 18+, one from each uploaded photo), fully clothed and instantly recognizable, brought together into one shared scene at <scene: golden-hour rooftop terrace with warm sky glow and a blurred city skyline (default), nighttime train interior with blue bench seating and window reflections, sunlit garden path, or user-described setting>, faces, hairstyles and body types kept exactly, <pose: a standing embrace with a forehead touch, arms settled around each other (default), a seated embrace with one leaning into the other, a lift-spin reunion, or user-described pose>, soft cinematic light wrapping the couple, warm romantic mood, non-explicit, tasteful, no kissing required. Posed for motion, clear subject, cinematic light. Nothing from the original photo's background remains. ``` **MOTION** (motion only; the frame already shows the look) ```text Starting from this exact frame: the two adults slowly draw closer, shoulders easing toward each other as one tilts their head and the other's arm settles gently around them; the embrace reaches its peak with a soft shared exhale and a faint smile, then settles into a calm, easy hold. The camera performs one slow push-in at a gentle speed, keeping both people centered. Preserve facial features and identity exactly: both keep their own faces, hairstyles and outfits, no feature swapping, n