UGC AI Video Ad Prompts with Product and Scale Lock
Shot-by-shot prompts for AI UGC video ads that keep the creator, product details, and product size consistent from clip to clip.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help you create a prompt for generating a UGC-style video. That's a useful format for ads. To make it work well with AI video generation, you'd want to include details about the character, the product, the setting, and the action you want to happen. I could put together a prompt that describes those elements, but it would be more effective if I understood what kind of vibe you're going for. Is this supposed to feel authentic and spontaneous, or more polished? And do you have an ideal length in mind? Once I know more, I can structure the prompt better.
UGC PROMPT STRUCTURE — Sports Water Bottle Ad: CHARACTER REFERENCE: • Female, early 30s, athletic build, natural energy • Wearing: gym clothes (black leggings, gray tank top, minimal makeup) • Setting context: morning workout routine, mid-jog energy • Tone: enthusiastic but authentic, no corporate language PRODUCT REFERENCE: • 24oz insulated water bottle (bright blue with gradient) • Key feature: stays cold for 24 hours • Benefit shown in ad: keeps water ice-cold during entire 5-mile run • No specs dumping — show benefit through action, not voiceover SCALE REFERENCE: • Show bottle in hand for size comparison • Fit in standard cup holder • Weight feels substantial but not heavy SCENE BREAKDOWN (30 seconds): → 0-3s: Character filling bottle at kitchen sink, comment: "About to crush 5 miles" → 3-15s: Running montage, character takes sips, remarks bottle still cold at halfway point → 15-25s: Post-run, character pours water into glass, ice cubes still visible, "Still cold, still going" → 25-30s: Product shot, character smiles, subtle call-to-action: "Get yours for 35 dollars" TONE GUARDRAILS: • Avoid fitness influencer cliches (gym flexing, overly polished) • Keep it relatable and conversational • No music, just natural sound (breathing, water pour, footsteps) INPUT TO AI VIDEO GENERATOR: Above structure ready for Higgsfield MCP end-to-end generation.
About this skill
Your AI UGC ad looks like a stock commercial. The bottle is as tall as the creator's forearm, the logo melts halfway through, and the person's face changes between clips. This skill writes prompts that prevent those problems. It fixes the product's details from real photos, ties its size to the creator's body, and asks for phone-camera realism instead of a studio look.
What it does
- Writes one reusable character block, product block, and scale block that are pasted unchanged into every shot, so the ad stays consistent
- Uses an image-first workflow: it makes one still frame of the creator holding the product, then animates that frame, so the product keeps its details
- Ties product size to the creator's hands, forearm, or furniture, and gives exact dimensions
- Turns a hook-problem-demo-proof-CTA script into one short, single-action prompt per clip, with spoken lines short enough to fit the clip
- Swaps polish words like cinematic, studio lighting, and flawless skin for realistic phone-camera details
- Points out shots likely to fail, such as pouring, peeling, or close-ups of small text, and flags claims or disclosures that need a compliance check
What you get
A ready-to-paste prompt pack: character, product, and scale blocks, a prompt for the still frame, a numbered shot list with one video prompt and its spoken line per clip, and a short checklist for reviewing each generated clip.
Best for
DTC brands, performance marketers, and agencies who make AI UGC ads with image and video models. Especially useful if you're stuck on wrong product size, morphing logos, or creators who look too polished to pass as real customers.
SKILL.md preview
---
name: ugc-ai-video-ad-prompts
description: Writes shot-by-shot prompts for UGC-style AI video ads, and gives matching shoot advice when real creators film. It fixes three reusable blocks (a character block, a product block taken from real product photos, and an explicit scale anchor), makes one still frame, then animates it with image-to-video. Use when the user says "write a UGC prompt for our product", "make an AI UGC ad", "turn this script into video prompts", "my AI video makes the product the wrong size", "the logo keeps morphing", "the creator looks too fake and polished", "the face changes between clips", "how do I keep a small product visible in UGC".
---
… (sign up to view the full skill)More creator skills
View all Creator skills →Explainer B-Roll Prompt Pack for AI Video
Turns a VO transcript into a style-locked AI video prompt pack: coverage map, P1-P3 clips timed to the VO, exact data routed to code.
Seedance Scene Prompts: Action, Dialogue and Blockouts
Seedance prompts for scenes with people: weighty action, living performances, timed dialogue, multi-clip continuity, and blockout v2v.
Faceless 3D Animated Shorts Pipeline
Concept, timed narration, style bible, and per-scene image, motion, VO, and SFX prompts for faceless 3D shorts that stay consistent.
Seedance 2.0 Video Prompt Writer
Turns an idea into a timecoded multi-shot Seedance 2.0 prompt with camera moves, continuity, reference roles, and synced sound cues.