Halloween Haunted Castle Image-to-Video · skill pubblica Open Skill
Halloween Haunted Castle Image-to-Video
Halloween Haunted Castle Image-to-Video è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284861/2026-10-15/24bvbx8u.gif
# Halloween Haunted Castle Image-to-Video Deliver one **short vertical (9:16) Halloween cinematic clip** (default **12 seconds** unless the user asked for another length). The person moves through an **ancient haunted castle corridor** while the camera **tracks the figure, then orbits around to reveal the front**. **Facial identity lock:** keep the reference person's **exact facial features and recognizability**; **clothing, background, props, and lighting** may shift to Halloween haunted-castle styling. **Upload path:** optional hero still polish, then **`ref2v`** with the locked castle-corridor prompt and embedded ambient audio when the model supports it. **Direct generate:** text-to-image **three-quarter or full-body keyframe** of an original adult, then the same pipeline—**upload is never required**. Prompt templates and camera beats live in `references/`. No structured project state. **Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image`, `generate_video`, and `video_agent` `instruction` is **English**. Do not tell the user tool names, channel names, or dump full prompts. ## User-visible speech (hard) **Allowed lines only:** - Need input: one short note that they may **upload a portrait**, **describe the subject**, or **tap direct generate**—then pause **P-empty** or **P-brief**. - Starting generate: at most **one** short line (user language), then tool calls only—**no** `set_guidance` on that turn. - Success: one or two sentences that the **haunted castle corridor clip** is ready—no URL, no prompt dump. Pause **P-done**. - Tool failure: brief honest note. Pause **P-fail**. - Safety block: one polite refusal. Pause **P-refuse**. If the user already asked to **generate**, tapped **direct generate**, or sent a one-shot create message, **do not** re-ask—read the prompt references, apply defaults, and generate. ## Pause = clickable buttons (hard) Any turn that **stops without a new shown final video**, and **every success turn**, must end with: 1. One or two short sentences (user language). 2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.** Do **not** call `set_guidance` in the same turn as `generate_image`, `generate_video`, `video_agent`, or `recognize_image`. Each button is an object with `text` and `action` (not bare strings): - **`send_message`**: `content` is the full sentence sent when tapped. - **`fill_input`**: `content` is starter text the user can edit. Offer **2–4** options. Localize `text` and `content` to the user's language. No channel or tool names on buttons. Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`. | Pause | When | Example intents (localize) | |---|---|---| | P-empty | No upload, no subject brief, no direct-generate tap, no last clip to refine | Direct generate castle clip · Upload my photo · Describe my character | | P-brief | Wants the castle clip but no mood or wardrobe cues and no upload | Direct generate default · fill_input custom character · Upload photo instead | | P-refuse | Minor in sexualized context, non-consensual deepfake, hate, graphic gore, NSFW staging | Direct generate fictional adult · Upload a different photo | | P-fail | Generation or `video_agent` `success=false` after retry | Direct generate again · Regenerate video from last still · More ghosts and lightning | | P-done | Final castle corridor clip ready | Direct generate new character · Upload my photo · More ghosts · Warmer amber candles | ## When to use - User wants a **Halloween haunted castle corridor** video with **track-then-orbit camera** and **identity-locked face** from a photo or invented character. - User uploads a **portrait** and wants a **cinematic, atmospheric** castle sequence with ghosts, drapes, candlelight, and lightning. - User has **no photo** or taps **direct generate**—run **T2I keyframe + ref2v** using de