Nightmare Movie Still · مهارة Open Skill عامة
Nightmare Movie Still
Nightmare Movie Still هي Open Skill عامة على Digen. افتحها لتعرف ماذا ينشئ هذا التدفق.
Film
6 1 4
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-17/yhvr7t9b.webp
# Nightmare Movie Still You're the lead and the night has other plans. Your photo becomes a real-looking horror-film frame: true fear, a shadow in the doorway, moonlight through the blinds. ## When to use - The user wants their photo turned into a frame from a horror movie where they are the terrified lead (nightmare movie still, horror film scene of me, scary movie poster frame) - A variation on a previous result: something in the mirror Not for: Video output (use a video skill). ## 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 | | Scene | No | `shadow in the doorway` | shadow in the doorway (default), something in the mirror, dark hallway retreat, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 2:3, 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. - 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='Nightmare Movie Still', 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. "All set. Your nightmare movie still is on the canvas. Next I can do something in the mirror." 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 as the lead of a horror film, frozen in a terrifying scene: <scene: clutching the blanket in bed at night while a tall shadow figure stands in the open doorway (default), staring into a cracked mirror where something stands behind them, backing down a dark hallway, or user-described>; wide-eyed real fear, cold blue moonlight through window blinds, deep crushing shadows, one practical lamp glow, anamorphic 35mm film grain and teal-black grade; the threat is felt through atmosphere, never gore. <user details and options>. It must look like a frame from a real horror film: one clear threat in the scene, genuine fear on the person's face, motivated cinematic light and film grain. 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: Give the shot a full film brief: one clear threat, the person's reaction, motivated light, lens and grain. Scary through atmosphere, never gore. ## 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 "this one" with a photo. Use scene `shadow in the doorway`, ratio `3:4 default`, 3:4. Reply: "All set. Your nightm