Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Here's how I create hyper-realistic AI UGC that actually stops the scroll: → Source real faces & locations from Pinterest for reference → Study viral TikTok hooks — the pacing, the framing, the delivery → Run it through Seedance using both as reference The prompt structure: "Replace the girl... show more

George Stock

47,296 subscribers

25,149 views • 4 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Just made this with Seedance. Full workflow, start to finish: - Grab a reference image — TikTok, Instagram, or Pinterest - Upload it to Claude, write a JSON prompt, adjust as you like - Generate the image - Upload it to Seedance 2.5 with your full video prompt Done All inside MakeUGC, for $1. I made a full guide breaking down the exact JSON prompt structure that makes this work. Comment "JSON" and I'll send it over

Just made this with Seedance. Full workflow, start to finish: - Grab a reference image — TikTok, Instagram, or Pinterest - Upload it to Claude, write a JSON prompt, adjust as you like - Generate the image - Upload it to Seedance 2.5 with your full video prompt Done All inside MakeUGC, for $1. I made a full guide breaking down the exact JSON prompt structure that makes this work. Comment "JSON" and I'll send it over

Cas.Fyn

15,013 views • 2 days ago

A cinematic travel moment through a beautiful heritage garden Capturing the architecture, flowers, and golden vibes in one smooth vlog. Created on seedance 2.0 Prompt: Create a 14-second cinematic travel vlog using the provided image as the exact location reference. Show a stylish young girl vlogging while walking through this beautiful heritage garden, keeping the same grand historic building, colorful flowers, wet pathway, greenery, palm trees and overall atmosphere from the reference image. Start with a wide establishing shot of the location, then show the girl smiling and talking naturally to her camera, turning the camera to reveal the beautiful surroundings. Include smooth walking shots, close-ups of flowers and architecture, natural reactions and a joyful spin. Use warm golden sunlight, realistic people, cinematic depth of field, smooth handheld/gimbal movement, natural ambient city sounds and ultra-realistic 4K quality. End with a beautiful wide shot of the same location. No text, no logos, no artificial-looking elements, and preserve the reference location accurately.

A cinematic travel moment through a beautiful heritage garden Capturing the architecture, flowers, and golden vibes in one smooth vlog. Created on seedance 2.0 Prompt: Create a 14-second cinematic travel vlog using the provided image as the exact location reference. Show a stylish young girl vlogging while walking through this beautiful heritage garden, keeping the same grand historic building, colorful flowers, wet pathway, greenery, palm trees and overall atmosphere from the reference image. Start with a wide establishing shot of the location, then show the girl smiling and talking naturally to her camera, turning the camera to reveal the beautiful surroundings. Include smooth walking shots, close-ups of flowers and architecture, natural reactions and a joyful spin. Use warm golden sunlight, realistic people, cinematic depth of field, smooth handheld/gimbal movement, natural ambient city sounds and ultra-realistic 4K quality. End with a beautiful wide shot of the same location. No text, no logos, no artificial-looking elements, and preserve the reference location accurately.

liana

10,463 views • 1 month ago

This guy transforms into top OnlyFans models with one click 6.4M views in 3 weeks. nobody can tell which face is real the workflow: -> Pinterest → 2 contrasting faces -> Nano Banana Pro → merge into one AI face -> Kling → transfer movement from a real reference video -> CapCut → remove the AI plastic look 30 minutes from zero to a viral AI girl the article below breaks down the exact prompts and settings 👇

Sensitive content

This guy transforms into top OnlyFans models with one click 6.4M views in 3 weeks. nobody can tell which face is real the workflow: -> Pinterest → 2 contrasting faces -> Nano Banana Pro → merge into one AI face -> Kling → transfer movement from a real reference video -> CapCut → remove the AI plastic look 30 minutes from zero to a viral AI girl the article below breaks down the exact prompts and settings 👇

Paone

225,949 views • 4 months ago

Editors are becoming optional for ad creative. I built a workflow that takes any viral video ad and rebuilds it with your product in it — in a couple of minutes. What it does: - Analyzes the reference ad's style — backgrounds, typography, zooms, pacing - Rebuilds it with your product, your face, your voice - No timeline, no manual cutting, no editor needed Input: raw clip + reference video Output: finished ad Comment "CLONE" and I'll DM you the workflow (must be following) 👇

Editors are becoming optional for ad creative. I built a workflow that takes any viral video ad and rebuilds it with your product in it — in a couple of minutes. What it does: - Analyzes the reference ad's style — backgrounds, typography, zooms, pacing - Rebuilds it with your product, your face, your voice - No timeline, no manual cutting, no editor needed Input: raw clip + reference video Output: finished ad Comment "CLONE" and I'll DM you the workflow (must be following) 👇

George Stock

10,696 views • 1 month ago

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.

Zentrix⌚️

14,015 views • 2 months ago

The ultimate portrait setup pro tip from Tristan Zhou with the Xperia 5 IV and Sony | Alpha: "Use the Xperia as a reference monitor for the model (screen facing the model), so they know how they look in real time during the photoshoot!" #SonyXperia

The ultimate portrait setup pro tip from Tristan Zhou with the Xperia 5 IV and Sony | Alpha: "Use the Xperia as a reference monitor for the model (screen facing the model), so they know how they look in real time during the photoshoot!" #SonyXperia

Sony | Xperia US

18,651 views • 3 years ago

i just generated this AI UGC creative for a teeth whitening product in 10 minutes in Higgsfield (you can now generate in 1080p)... here's my workflow: > deploy a research agent to find UGC style videos that promote products like the one you wanna make a creative for > use gemini 2.5 flash to analyze the creative & get a detailed analysis of each scene (get it to add a placeholder for each image reference in your prompt) > use GPT-image 2 in Higgsfield to extract a frame from each cut-scene & use it as a reference for your generation in the prompt wherever there's a placeholder > send the prompt + all the references to Higgsfields video generator & select Seedance 2.5, then generate it > once you have a finished product, take it to a video editor & add captions / cuts / zooms / music

i just generated this AI UGC creative for a teeth whitening product in 10 minutes in Higgsfield (you can now generate in 1080p)... here's my workflow: > deploy a research agent to find UGC style videos that promote products like the one you wanna make a creative for > use gemini 2.5 flash to analyze the creative & get a detailed analysis of each scene (get it to add a placeholder for each image reference in your prompt) > use GPT-image 2 in Higgsfield to extract a frame from each cut-scene & use it as a reference for your generation in the prompt wherever there's a placeholder > send the prompt + all the references to Higgsfields video generator & select Seedance 2.5, then generate it > once you have a finished product, take it to a video editor & add captions / cuts / zooms / music

EP

28,949 views • 28 days ago

Testing Seedance vs Google Omni for VFX style stuff Seedance is vastly superior in every test I have done. Prompt: "Replace the background with an enormous sea creature pursuing the boat. Have it end with the creature catching up and just about to swallow the boat. Match the exact verbatim camera angle and position of the boat from the reference video."

Testing Seedance vs Google Omni for VFX style stuff Seedance is vastly superior in every test I have done. Prompt: "Replace the background with an enormous sea creature pursuing the boat. Have it end with the creature catching up and just about to swallow the boat. Match the exact verbatim camera angle and position of the boat from the reference video."

A.I.Warper

18,185 views • 2 months ago

You can generate endless short animated stories with this method using just a reference image. A mini prompt for Seedance 2.0 Mini: Funny English narrative story between the girl and the silly donkey named biscuits, presented in cinematic coverage with dynamic angles - 8 Shots Midjourney v8.2 Prompt for reference image, you don't need to tag it. girl with silly donkey --ar 16:9 --sref 3732263062 --profile txgf1m1 --stylize 1000 --preview

Kōda

12,339 views • 2 months ago

i'm LEAKING our entire AI UGC hook library: we use these EXACT 50 openers to stop the scroll across every client account we run... this is literally the difference between content nobody sees and content that goes VIRAL. like + comment "HOOKS" and i'll send it over (must be following + RT for priority access)

i'm LEAKING our entire AI UGC hook library: we use these EXACT 50 openers to stop the scroll across every client account we run... this is literally the difference between content nobody sees and content that goes VIRAL. like + comment "HOOKS" and i'll send it over (must be following + RT for priority access)

Adrian Solarz

28,083 views • 1 month ago

Kling 2.6 Motion Control is absolutely insane 🤯 Take any reference video and transfer the exact motion onto an AI character: full-body sync, facial expressions, hand gestures, everything. All with just a few clicks. Perfect for e-comm brands and agencies creating AI video ads that don't look like AI. Here's the problem: AI-generated video ads still look robotic. The movements are stiff, the expressions are flat. Your audience clocks it as AI instantly and keeps scrolling. Kling 2.6 Motion Control fixes it: → Start with any reference clip (stock footage, existing UGC, motion reference) → Upload to Kling → Map the exact movement onto any AI character → Full-body motion, hand gestures, facial expressions—all transferred → Generate up to 30 seconds of video No stiff AI movements, no uncanny valley, no instant "skip this ad" reaction. What this unlocks: - Use one winning UGC motion → swap in different AI creators - Pull reference clips from anywhere → generate branded variations - Create dynamic AI video ads with real human movement - Test multiple "creators" without filming anyone new I recorded a quick walkthrough showing how to do this step-by-step. Want access? > Comment "KLING" > Like this post And I'll send it over (must be following so I can DM)

Kling 2.6 Motion Control is absolutely insane 🤯 Take any reference video and transfer the exact motion onto an AI character: full-body sync, facial expressions, hand gestures, everything. All with just a few clicks. Perfect for e-comm brands and agencies creating AI video ads that don't look like AI. Here's the problem: AI-generated video ads still look robotic. The movements are stiff, the expressions are flat. Your audience clocks it as AI instantly and keeps scrolling. Kling 2.6 Motion Control fixes it: → Start with any reference clip (stock footage, existing UGC, motion reference) → Upload to Kling → Map the exact movement onto any AI character → Full-body motion, hand gestures, facial expressions—all transferred → Generate up to 30 seconds of video No stiff AI movements, no uncanny valley, no instant "skip this ad" reaction. What this unlocks: - Use one winning UGC motion → swap in different AI creators - Pull reference clips from anywhere → generate branded variations - Create dynamic AI video ads with real human movement - Test multiple "creators" without filming anyone new I recorded a quick walkthrough showing how to do this step-by-step. Want access? > Comment "KLING" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

25,247 views • 7 months ago

recreated this exact hook with AI in 3 minutes generated first frame with nano banana -> uploaded it along with reference video to Kling motion control, done when the quality is actually there, AI UGC beats real creators every time we built the best system for this right now: - realistic visuals - realistic voice - realistic movement - all optimized for virality and conversions way cheaper than a real creator and built for scale across thousands of posts and multiple accounts this isn't generic AI slop, these are high quality systems built with real effort and ready to scale your business it works across ecom,apps, saas, coaching, DTC... everything yet people are still paying $300-500 per UGC video from creators who ghost halfway through the project

recreated this exact hook with AI in 3 minutes generated first frame with nano banana -> uploaded it along with reference video to Kling motion control, done when the quality is actually there, AI UGC beats real creators every time we built the best system for this right now: - realistic visuals - realistic voice - realistic movement - all optimized for virality and conversions way cheaper than a real creator and built for scale across thousands of posts and multiple accounts this isn't generic AI slop, these are high quality systems built with real effort and ready to scale your business it works across ecom,apps, saas, coaching, DTC... everything yet people are still paying $300-500 per UGC video from creators who ghost halfway through the project

MAX

171,662 views • 6 months ago

I built a workflow that copies any viral video ad It's stupidly easy. Takes a couple of minutes. Show it one viral ad → it clones the whole style. Backgrounds, typography, zooms, cut rhythm, pacing. Swaps in your product, your face, your voice. Never opened a timeline. One workflow. Raw clip + reference video in → finished ad out. Comment "COPIE" and I'll DM you the WORKFLOW (must be following)

I built a workflow that copies any viral video ad It's stupidly easy. Takes a couple of minutes. Show it one viral ad → it clones the whole style. Backgrounds, typography, zooms, cut rhythm, pacing. Swaps in your product, your face, your voice. Never opened a timeline. One workflow. Raw clip + reference video in → finished ad out. Comment "COPIE" and I'll DM you the WORKFLOW (must be following)

Stijn Feijen

18,174 views • 1 month ago

Claude + Seedance 2.0 = 50 Viral UGC Videos a Day Fully realistic UGC ads. Cinematic lighting. Natural movement. Clean pacing. Here's what it does: → Generates scripts and hooks automatically → Renders AI creators who look and move like real people → Tests angles against each other in real time → Scales what wins without touching the process It's already live. Campaigns are scaling. Want the full setup? Comment "UGC" (must be following)

Claude + Seedance 2.0 = 50 Viral UGC Videos a Day Fully realistic UGC ads. Cinematic lighting. Natural movement. Clean pacing. Here's what it does: → Generates scripts and hooks automatically → Renders AI creators who look and move like real people → Tests angles against each other in real time → Scales what wins without touching the process It's already live. Campaigns are scaling. Want the full setup? Comment "UGC" (must be following)

Stijn Feijen

14,870 views • 2 months ago

gemini omniflash is actually f*cking cracked. you can animate/edit any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.

gemini omniflash is actually f*cking cracked. you can animate/edit any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.

Sulfur

36,652 views • 2 months ago

seedance 2.0 is now the best model for AI UGC this video was free and took me 30 seconds to make it handles realism better than any model ive seen yet, and it understands different creative styles i gave it a very vague prompt then it handled the rest now imagine what you could do with more reference photos, detailed structured prompting etc lots of possibilities with this

seedance 2.0 is now the best model for AI UGC this video was free and took me 30 seconds to make it handles realism better than any model ive seen yet, and it understands different creative styles i gave it a very vague prompt then it handled the rest now imagine what you could do with more reference photos, detailed structured prompting etc lots of possibilities with this

Miko

42,184 views • 7 months ago

Google VEO 3 just announced 9:16 videos and it's absolutely WILD 🤯 This AI system creates hyper-realistic UGC-style ads in vertical format. And generates multiple clips that look like real creator content. Perfect for e-comm operators & ad agencies running Facebook/TikTok campaigns. But instead of hiring UGC creators, managing shoots, and editing content... Just upload a reference image and get authentic-looking vertical ads that convert. Here's what makes it so good: → Google VEO 3 now supports native 9:16 aspect ratio → Creates hyper-realistic UGC-style content automatically → Generate multiple clip variations from one reference → Nano Banana integration for ultra-realistic characters → Minimal editing required for campaign-ready content → Perfect for Facebook/Instagram/TikTok ads & organic I filmed a full Loom walkthrough showing exactly how I did this with the exact prompts. Want access to the complete tutorial? Comment "VEO" + like + bookmark and I'll send it right over (must be following so I can DM)

Google VEO 3 just announced 9:16 videos and it's absolutely WILD 🤯 This AI system creates hyper-realistic UGC-style ads in vertical format. And generates multiple clips that look like real creator content. Perfect for e-comm operators & ad agencies running Facebook/TikTok campaigns. But instead of hiring UGC creators, managing shoots, and editing content... Just upload a reference image and get authentic-looking vertical ads that convert. Here's what makes it so good: → Google VEO 3 now supports native 9:16 aspect ratio → Creates hyper-realistic UGC-style content automatically → Generate multiple clip variations from one reference → Nano Banana integration for ultra-realistic characters → Minimal editing required for campaign-ready content → Perfect for Facebook/Instagram/TikTok ads & organic I filmed a full Loom walkthrough showing exactly how I did this with the exact prompts. Want access to the complete tutorial? Comment "VEO" + like + bookmark and I'll send it right over (must be following so I can DM)

Mike Futia

65,532 views • 11 months ago

It looks like these sketch-style storyboards work really well in Seedance 2.0. I'm going to stick with this approach for a while. In the video prompt, I only include intent, style, reference and visual approach. It follows the storyboard surprisingly well. I'm sharing below the GPT Image 2 prompt I use to create the previs, along with the video prompt I use afterwards. Created on @MartiniArt_

It looks like these sketch-style storyboards work really well in Seedance 2.0. I'm going to stick with this approach for a while. In the video prompt, I only include intent, style, reference and visual approach. It follows the storyboard surprisingly well. I'm sharing below the GPT Image 2 prompt I use to create the previs, along with the video prompt I use afterwards. Created on @MartiniArt_

Kōda

60,281 views • 4 months ago

Tried Higgsfield's motion control feature today and genuinely impressed. All I did was select a reference video and give it my own character sheet, and the output followed the reference motion almost perfectly, just with my character in it. Makes replicating a specific camera move or movement so much easier without having to prompt it from scratch. Worth trying if you haven't yet. Higgsfield AI 🧩

Tried Higgsfield's motion control feature today and genuinely impressed. All I did was select a reference video and give it my own character sheet, and the output followed the reference motion almost perfectly, just with my character in it. Makes replicating a specific camera move or movement so much easier without having to prompt it from scratch. Worth trying if you haven't yet. Higgsfield AI 🧩

Shara

25,380 views • 26 days ago

She makes $3k + a month from AI UGC so real your brain thinks she’s human. Chopsticks to lips. Micro skin texture. Visible pores. Individual eyebrow hairs. Reflections in her eyes. You saw light and skin and decided she was real. She isn’t. The workflow: Strong reference image → Gemini Image-to-JSON → Nano Banana Pro base model → 8 shots → Kling 3.0 animation with start/end frames → CapCut stitch with keyframes for one continuous take. One model. Dozens of reusable assets. Brands pay $60–$100 each. Most creators still fight blurry faces. She built the system once and now it prints on repeat. Comment UGC for the full prompt chain.

She makes $3k + a month from AI UGC so real your brain thinks she’s human. Chopsticks to lips. Micro skin texture. Visible pores. Individual eyebrow hairs. Reflections in her eyes. You saw light and skin and decided she was real. She isn’t. The workflow: Strong reference image → Gemini Image-to-JSON → Nano Banana Pro base model → 8 shots → Kling 3.0 animation with start/end frames → CapCut stitch with keyframes for one continuous take. One model. Dozens of reusable assets. Brands pay $60–$100 each. Most creators still fight blurry faces. She built the system once and now it prints on repeat. Comment UGC for the full prompt chain.

Rugikk

158,716 views • 2 months ago