Halloween Costume Talk · Open Skill 公開技能
Halloween Costume Talk
Hot pink lips, then a spooky quick change. That combo made me smile. My photo becomes a Halloween look with a matching backdrop, then I speak a short Halloween line in character. **floor notes:** - use a frontal adult photo you have the right to use, with your mouth mostly closed - pick a costume, like a classic vampire, witch, ghost host, or pumpkin royalty - keep the script short, around 2.5 to 3 words per second - choose warm, bright, calm, energetic, or serious, then start with 6 seconds What costume and line did you make? Post it here!
Film
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-17/5vu69umm.webp
# Halloween Costume Talk Costume on, scene set, lines ready. Your photo becomes a Halloween look with a matching backdrop — then you speak a short Halloween line in character. ## When to use - Make a photo speak a script, greeting or message - Redo with another mood or a shorter or longer script Not for: Singing to an existing song, or videos with several speakers. ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | Frontal adult face, mouth visible and ideally closed | | Script | Yes | — | About 2.5–3 words per second of video | | Description | No | tuned default below | What the user wants; merged into the prompt | | Costume | No | `classic vampire` | classic vampire (default), witch, ghost host, pumpkin royalty, or user-described | | Duration | No | `6 s` | 6 s (default), or 10 s | | Orientation | No | `9:16` portrait | Other ratios on request | | Mood | No | `warm` | warm, bright, calm, energetic, serious | - 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/lipsync-direction.md`. 2. **Face and gate check**: `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.')`. Decline minors; ask for a frontal photo if the mouth is hidden or the face is in profile. 3. **Length fit**: count the words. 6 s fits about 15 words and 10 s about 28. If the script is longer, offer a trimmed version or the 10 s length before generating. 4. **Look keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Halloween Costume Talk keyframe', entity_type='work_in_progress')`: frontal, mouth visible and closed, same face. If the face drifts, regenerate once. 5. **Voice**: `generate_tts(text=<script>, model='tts.design', voice_instruction=<VOICE>, name='Halloween Costume Talk voice', entity_type='voiceovers')`. 6. **Talking video**: `generate_video(prompt=<PERFORMANCE>, input_urls=[look keyframe], audio_url=<tts audio>, model='ai2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Halloween Costume Talk', entity_type='final_videos')`. The audio drives the mouth; never put audio in `input_urls`. 7. Reply in one or two sentences, e.g. "All set. Your halloween costume talk is on the canvas. Next I can do witch." 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. Intentional changes: the person now wears a full <costume: classic vampire (default), witch, ghost host, pumpkin royalty, or user-described> Halloween costume with matching hair styling and makeup, standing in a matching spooky-festive set (carved pumpkins, candlelight, purple night haze), warm orange key light and cool night rim light. Frontal medium close-up facing the camera, mouth visible and relaxed, eyes open, clean light on the face. Photoreal, fully clothed, no text. ``` **VOICE** ```text A natural <age range> <gender presentation> voice that suits the person, <mood delivery>, clear close-mic sound, no background music, native pronunciation in <script language>. ``` **PERFORMANCE** (describe the acting, never repeat the script) ```text the same adult in full Halloween costume in a spooky-festive set, playing it in character: a sly grin between phrases, eyebrows lifting on the fun line, a small conspiratorial lean toward the lens, candlelight flicker on the face, fully clothed costume. The person speaks directly to camera wit