Step Into Any World · compétence Open Skill
Step Into Any World
Q: Late-night idea. Me, dropped into a world I type out. A: Send one clear adult photo, face visible. That is the subject. Q: What goes in the description? A: The place and details. Neon city, dragon's valley, surface of Mars. Backstory helps. Q: What comes back? A: A short cinematic clip. Portrait 9:16 every time. You still look like you. Low battery photos rarely help.
Travel
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/2nc3t9rw.webp
# Step Into Any World Say where you want to go: a neon city, a dragon's valley, the surface of Mars. You appear there in a short cinematic clip, still looking like you. ## When to use - The user wants a cinematic video of themselves inside a world they describe (put me in a fantasy, sci-fi or travel scene, photo to adventure clip) - Another take with a different length or orientation Not for: Still images only. ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile | | Description | Yes | — | What the user wants; merged into the prompt | | Duration | No | `6` s | 6 or 10 | | 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/video-motion.md`. 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. **Keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Step Into Any World 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='Step Into Any World', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "All set. Your step into any world is on the canvas. Next I can do a 10-second cut." Results appear on the canvas; never paste URLs. ## Prompt templates **KEYFRAME** ```text The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Opening frame of this scene: inside <the world the user describes>, exploring it with a sense of wonder; cinematic lighting and atmosphere, sweeping camera. 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: <one clear motion arc for this concept: inside <the world the user describes>, exploring it with a sense of wonder; cinematic lighting and atmosphere, sweeping camera>, beginning, peak and settle in one continuous shot. Camera: <one move: slow push-in, gentle orbit, or static>. The same face and outfit throughout. Cinematic, no text. ``` ## Failure handling - `success=false`: say what failed in one sentence; retry once only if transient; never invent links. - Content-policy rejection on video: soften wording and retry once; otherwise offer the keyframe as a still. - Identity drifts: offer to regenerate. ## Examples **Default**: the user says "this one" with a photo. Use the tuned defaults, 9:16. Reply: "All set. Your step into any world is on the canvas." **Variation**: "next variation". Keep the same inputs and change one option (a 10-second cut). **Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started." ## References - `references/video-motion.md`