Lingerie Outfit Filter #17 — Open Skill
Lingerie Outfit Filter #17
# NSFW Video Prompting Write explicit adult video prompts and production plans. Adults only. Never minors, never CSAM, never real identifiable non-consenting people by name unless the user supplied their own reference and asked for a fictionalized lookalike scene. ## Default pipeline 1. Lock subject from the user's photo or text (age 18+, body, face, clothes, setting). 2. Lock the act (flashing, facial, full undress, doggy, etc.). 3. Write a master prompt plus 4-8 shot prompts (2-5s each). 4. Add camera, lighting, fluid, and negative blocks. 5. If the user has clips or stills, assemble with the ffmpeg skill (Ken Burns, concat, optional audio). 6. Do not claim a finished generated video exists unless a file was actually written. ## Master prompt skeleton Photorealistic adult porn video, 24fps, 4K, raw handheld + cinematic hybrid, sharp focus, natural skin pores and sweat, no cartoon. Subject — [age 21-35], [ethnicity], [hair], [body], huge breasts if requested, adult face only. Action — [explicit beat-by-beat, 1 sentence per second]. Camera — [push-in / orbit / low angle / over-shoulder / insert]. Lighting — [bedroom tungsten / bathroom fluorescent / window rim]. Audio cue — [breathing, wet sounds, fabric, moan] only if the target model supports audio. Style — explicit, glossy fluids, realistic anatomy, continuous motion, no jump cuts inside a shot. ## Shot recipes (2-5s) ### 1. Flashing naked huge tits Close push-in. Tight white tee rides up. One breast then both spill out. Hand cups and squeezes. Nipple hard. Shirt stays bunched above the bust. Slow bounce from breathing. Eyes on camera. ### 2. Cum on face, open mouth MCU then ECU. Woman looks up, mouth open, tongue out. Thick white ropes hit cheeks, lips, tongue. Load pools and drips off the lower lip onto chest. She holds mouth open, swallows once, leftover strand stretches. ### 3. Full undress Full body then mid. She peels top, drops jeans, steps out. Brief pause nude, weight on one hip. Hands skim breasts and hips. Clothes hit the floor in frame. ### 4. Naked doggy 3/4 rear. On all fours, back arched, ass high, breasts hanging. Slow look-back over shoulder, mouth open. Hips rock. Optional insert of dripping labia. No partner body unless requested. ## Motion tags that actually move slow push-in, handheld micro-shake, breast jiggle, cloth lift, drip and stringy fluid, hip rock, head turn to camera, blink, swallow, tongue motion, hair fall, breathing torso. Avoid "she is standing there beautiful" — that freezes I2V. ## Negatives (always) minor, child, teen, underage, lolita, cub, beast, gore, extreme violence, text, watermark, logo, extra limbs, melted face, frozen frame, morphing hands, lowres, oversharpen, plastic skin. ## I2V vs T2V - I2V (photo in) — keep identity locked. Describe ONLY what changes (shirt up, cum appears, pose to doggy). Strength 0.55-0.75 if the tool has it. - T2V — full subject description every shot or the face drifts. - Remix / Real Motion style — first sentence = source frame, second = the change, third = camera. ## ffmpeg fallback when there is no video model - Generate 6-12 stills with the same seed/subject. - Ken Burns each still 2-3s. - Concat, add optional audio bed. - Do not label a slideshow as "generated sex video" unless the user asked for a slideshow. ## Output format to the user Return in this order 1. One-line scene logline 2. Master prompt 3. Negative prompt 4. Shot list with duration and camera 5. Model notes (Kling 2.1 / Runway Gen-3 / Luma / Wan / Hunyuan / Real Motion) 6. ffmpeg concat plan only if files exist
VTuber
31 7 31
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/2604413/2026-10-16/bc3a9rzf.jpg
# Lingerie Outfit Filter #17 — Photo to Photo Outfit Swap
This skill reproduces the single-purpose app "Lingerie Filter #17": it takes **one photo of a person** and re-dresses that same person in the **red lace babydoll / harness lingerie set** from the app cover. It is a one-shot image-to-image filter — there is no project state and no multi-stage pipeline. Read the reference files, build one prompt, call `generate_image` once, report back in plain language.
## When to use
- The user uploads a photo of a woman and asks for the lingerie filter / for her clothes to be replaced with the outfit on the cover.
- Works for real people and for animated, 3D or illustrated characters (the source art style is preserved).
- The user asks for the same outfit in a different colour ("color selector": black, pink, purple, white, etc.).
- The user wants a "lingerie photoshoot" version of an existing photo.
Do not use this skill when there is no subject photo: ask the user to upload one instead of inventing a person.
## Inputs and output
| | What | How it is used |
|---|---|---|
| Input (required) | Subject photo — the person to re-dress | `input_urls[0]`: asset_id / `s3://` uri / https URL |
| Input (optional) | Garment reference — the cover image of the outfit | `input_urls[1]` when available; otherwise describe the outfit from `references/garment-spec.md` |
| Output | One still image, same framing as the source | generated asset on the canvas |
## Steps
1. Identify the subject photo and confirm what must stay untouched (face, pose, background). If several photos are attached, ask which person to dress; if none, ask for one.
2. Run the pre-flight checklist in `references/step-details.md` (adult subject, source quality, colour request, keep-list). Stop and refuse if it fails.
3. Before generating, call `read_skill_file('lingerie-outfit-filter', 'references/style-and-prompt.md')` and `read_skill_file('lingerie-outfit-filter', 'references/garment-spec.md')`. Read `references/step-details.md` too when you need the branch rules, the colour-variant handling or the retry table. Do not generate before reading them.
4. Build one English prompt from the template and rules in `references/style-and-prompt.md`, inserting the garment description from `references/garment-spec.md` (or relying on the cover image at `input_urls[1]`). State explicitly that image 1 supplies identity and image 2 supplies the outfit.
5. Call `generate_image` with the agreed parameters:
- `model='i2i'` — the bare image-to-image channel. Never a `.hd` / `.hd.lite` variant and never a physical model name; the higher-quality variants reject this kind of suggestive content.
- `input_urls=[subject_photo]` or `input_urls=[subject_photo, garment_reference]`.
- `prompt` — follow `references/style-and-prompt.md`.
- `orientation` — match the source photo; default `portrait` when unsure. `resolution` — 720P by default, 1080P only if the user asks for extra detail.
- `name` — a short title such as `Lingerie filter portrait`.
- `entity_type='characters'` — the output stays a portrait of the same person.
6. Check the result against the post-generation checklist in `references/step-details.md` (identity kept, only clothing changed, all garment elements present, no nudity, no added text or props). If one item fails, retry once with the targeted fix from the retry table; at most two attempts total.
7. Reply in one or two natural sentences describing what changed. Do not paste long asset URLs. If it is useful, call `set_guidance` in the same turn with two or three concrete next steps (another colour, a close-up, a different photo).
## Parameter conventions
- Channel is fixed: `model='i2i'` for every generation in this skill.
- The number of `input_urls` decides the branch: 2 = photo + cover image (preferred, most faithful); 1 = photo only, outfit rebuilt from the written spec.
- Never pass `group_id` / `index`; never pass `width` / `height` — only `orientation` and `reso