Lad

@ladprofit • 4,822 subscribers

Ai Ads and stuff

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

an AI singer just hit 418k monthly listeners on SPOTIFY her name is vyrma. she sings old norse viking folk - 185k subscribers on youtube - 333k followers on instagram - her top song has over 2 million plays on spotify her top 2 songs alone have made roughly $13,500 on spotify (at ~$0.004 a stream) the comments are the crazy part people know she's AI they listen ANYWAY and they're still asking for a concert meanwhile half of you are still trying to hide that your ads are AI she put it on her profile and grew anyway people don't skip AI they skip boring

46,831 views • 20 days ago

saw iman run this INFOTAINMENT style ad this ad format is SNEAKY low poly 3D world. calm narrator explaining gives those old school informative youtube vibes, the kind of explainer you'd binge at 2am without noticing the time then somewhere around "financial goals" it quietly turns into a pitch for a second stream of income why it works: - no talking head, no lipsync, zero "hey guys" energy that screams sponsored - word by word captions keep your eyes locked - one red character so your brain always knows who the story is about - one render style + one voiceover + a pile of short scenes. dirt cheap to make with AI, no actors, no faces to keep consistent you've watched 100 seconds before you realize it's an ad by then it's too late tell me this isn't the most underrated ad format on IG rn

saw iman run this INFOTAINMENT style ad this ad format is SNEAKY low poly 3D world. calm narrator explaining gives those old school informative youtube vibes, the kind of explainer you'd binge at 2am without noticing the time then somewhere around "financial goals" it quietly turns into a pitch for a second stream of income why it works: - no talking head, no lipsync, zero "hey guys" energy that screams sponsored - word by word captions keep your eyes locked - one red character so your brain always knows who the story is about - one render style + one voiceover + a pile of short scenes. dirt cheap to make with AI, no actors, no faces to keep consistent you've watched 100 seconds before you realize it's an ad by then it's too late tell me this isn't the most underrated ad format on IG rn

32,878 views • 21 days ago

the best AD FORMAT i've seen in months came from scrolling past dave ramsey on instagram a call-in advice show. authoritative host behind a desk takes a live call from a woman who can't sleep, diagnoses her problem on air, and recommends the fix with the kind of quiet confidence that makes you forget you're watching an ad quick workflow: - generated a single studio shot of the host at his desk and used it as the identity lock for all six clips - the caller is audio-only through his headset, so there's no second face to keep consistent across cuts - wrote full performance direction into every Omni prompt: the southern drawl, the listening beats where his mouth stays shut, the product pickup - rendered all six clips and stitched in CapCut, nothing reshot the format works because the host sounds like he's run this show for twenty years, and the caller's exhaustion is relatable RT + reply 'DAVE' and i'll send you the full workflow (must follow so i can dm)

the best AD FORMAT i've seen in months came from scrolling past dave ramsey on instagram a call-in advice show. authoritative host behind a desk takes a live call from a woman who can't sleep, diagnoses her problem on air, and recommends the fix with the kind of quiet confidence that makes you forget you're watching an ad quick workflow: - generated a single studio shot of the host at his desk and used it as the identity lock for all six clips - the caller is audio-only through his headset, so there's no second face to keep consistent across cuts - wrote full performance direction into every Omni prompt: the southern drawl, the listening beats where his mouth stays shut, the product pickup - rendered all six clips and stitched in CapCut, nothing reshot the format works because the host sounds like he's run this show for twenty years, and the caller's exhaustion is relatable RT + reply 'DAVE' and i'll send you the full workflow (must follow so i can dm)

106,559 views • 2 months ago

built a BREAKING NEWS style ad with AI and it's terrifying how convincing it is synthetic spokesperson, invented product, "doctor" with credentials I generated, and the only thing standing between this and a multimillion-dollar lawsuit is a disclosure line I burned into the bottom in 6pt font which, deeply funny to me, is currently doing more work to keep this legal than any advertising regulation is quick workflow: - locked a trustworthy face and an "expert" as two separate characters, same identity held across every clip - built the studio set once, product claims baked into the reference stills since AI video still can't reliably generate on-screen text on its own - wrote it as a straight pitch-to-testimonial rhythm, problem, solution, social proof, genuine commercial structure - animated every clip locked off, zero camera movement, because a shaky "infomercial" would've broken the illusion instantly if you're testing AI UGC formats, this broadcast style is one of the more convincing ones I've built and worth having in the rotation RT + reply 'NEWS' and i'll send you the workflow including compliance workarounds (must follow so i can DM)

built a BREAKING NEWS style ad with AI and it's terrifying how convincing it is synthetic spokesperson, invented product, "doctor" with credentials I generated, and the only thing standing between this and a multimillion-dollar lawsuit is a disclosure line I burned into the bottom in 6pt font which, deeply funny to me, is currently doing more work to keep this legal than any advertising regulation is quick workflow: - locked a trustworthy face and an "expert" as two separate characters, same identity held across every clip - built the studio set once, product claims baked into the reference stills since AI video still can't reliably generate on-screen text on its own - wrote it as a straight pitch-to-testimonial rhythm, problem, solution, social proof, genuine commercial structure - animated every clip locked off, zero camera movement, because a shaky "infomercial" would've broken the illusion instantly if you're testing AI UGC formats, this broadcast style is one of the more convincing ones I've built and worth having in the rotation RT + reply 'NEWS' and i'll send you the workflow including compliance workarounds (must follow so i can DM)

90,537 views • 2 months ago

this TRUE CRIME ad had no human editor claude code searched a free film library, picked the shots and cut them on the narrator's words 42 s. 25 cuts. no timeline. 1958: a bank mails 60,000 people a credit card nobody asked for case file -> suspects -> case closed quick workflow: > internet archive API = 15 film clips, $0 > claude reads the frames, picks each shot > every cut lands on a spoken word > stamps + exhibits = code, timed to the voice > only 6 of 21 shots generated most b-roll doesn't need generating it already exists RT + reply 'FILE' and i'll send you the full workflow (must follow so i can dm)

this TRUE CRIME ad had no human editor claude code searched a free film library, picked the shots and cut them on the narrator's words 42 s. 25 cuts. no timeline. 1958: a bank mails 60,000 people a credit card nobody asked for case file -> suspects -> case closed quick workflow: > internet archive API = 15 film clips, $0 > claude reads the frames, picks each shot > every cut lands on a spoken word > stamps + exhibits = code, timed to the voice > only 6 of 21 shots generated most b-roll doesn't need generating it already exists RT + reply 'FILE' and i'll send you the full workflow (must follow so i can dm)

10,563 views • 8 days ago

most people still don't comprehend how far AI video has come. no memory between clips used to mean every cut reset the scene, drifted, redrew itself. that's basically solved now if you build around it right this whole ad is one continuous WHITEBOARD, 9 chained clips, and the marker ink never moves, never redraws, never resets to a blank board. here's exactly how, so you can build your own version of this for any product the trick: OMNI flash has a hard 10 second limit per clip and zero memory of the clip before it. so you harvest the last frame of clip N, the board exactly as it looks at that instant, and feed it in as the starting frame of clip N+1. that's the entire mechanism. no cuts, no set, just a hand, a marker, and one continuous illusion the flow: - map your script to the arc: symptom, invisible cause, mechanism, solution, real product - write the VO as one continuous read, then split it into beats, ~20-25 words max per clip, one drawing action per clip - build a board map first, what's written and drawn on each row, so nothing collides as it fills up - generate clip 1, harvest its last frame, chain into clip 2, repeat - once the board gets dense (4-5 clips of ink in), "match the board" - stops being enough instruction. name every existing element explicitly, state a hard no-touch rule, and point at your target by position, not just by text, or the model will grab the wrong line - save the reveal for last: a real product photo beats a drawn one almost every time PROMPT: locked blocks, paste verbatim into every single clip STYLE: "Real documentary UGC footage, static locked camera on a dry-erase whiteboard, one real human hand and forearm only, never show a face or body. A single black marker is used for the entire clip, no color changes, no marker switching. Marker ink renders as genuine dry-erase marker, not a digital text or motion-graphic overlay. Handwriting is plain block capitals, legible at a glance. Icons stay minimal and schematic, one simple recognizable shape only. No captions, no subtitles, no on-screen text beyond what the hand physically writes or draws. ASPECT: 9:16 vertical." VOICE: "VOICEOVER (calm, warm, explanatory, American English, mid-30s):" opening clip, full prompt: "An 8-second locked-camera whiteboard explainer, vertical 9:16. Open on a blank white dry-erase board, static tripod shot, no camera movement, no zoom. 00:00-00:05: The hand writes your hook headline in black marker, plain block capitals, upper-left, then underlines it, natural handwriting speed, ink appears stroke by stroke, slight squeak. 00:05-00:08: The hand draws one small icon, upper-right. VOICEOVER: your hook line. AUDIO: marker squeak, quiet room tone underneath. No music. [STYLE LOCK]" every clip after that opens with "use the attached image, [clip N-1]'s final frame, as the opening frame, match the exact board state precisely" before describing the one new action for that beat

most people still don't comprehend how far AI video has come. no memory between clips used to mean every cut reset the scene, drifted, redrew itself. that's basically solved now if you build around it right this whole ad is one continuous WHITEBOARD, 9 chained clips, and the marker ink never moves, never redraws, never resets to a blank board. here's exactly how, so you can build your own version of this for any product the trick: OMNI flash has a hard 10 second limit per clip and zero memory of the clip before it. so you harvest the last frame of clip N, the board exactly as it looks at that instant, and feed it in as the starting frame of clip N+1. that's the entire mechanism. no cuts, no set, just a hand, a marker, and one continuous illusion the flow: - map your script to the arc: symptom, invisible cause, mechanism, solution, real product - write the VO as one continuous read, then split it into beats, ~20-25 words max per clip, one drawing action per clip - build a board map first, what's written and drawn on each row, so nothing collides as it fills up - generate clip 1, harvest its last frame, chain into clip 2, repeat - once the board gets dense (4-5 clips of ink in), "match the board" - stops being enough instruction. name every existing element explicitly, state a hard no-touch rule, and point at your target by position, not just by text, or the model will grab the wrong line - save the reveal for last: a real product photo beats a drawn one almost every time PROMPT: locked blocks, paste verbatim into every single clip STYLE: "Real documentary UGC footage, static locked camera on a dry-erase whiteboard, one real human hand and forearm only, never show a face or body. A single black marker is used for the entire clip, no color changes, no marker switching. Marker ink renders as genuine dry-erase marker, not a digital text or motion-graphic overlay. Handwriting is plain block capitals, legible at a glance. Icons stay minimal and schematic, one simple recognizable shape only. No captions, no subtitles, no on-screen text beyond what the hand physically writes or draws. ASPECT: 9:16 vertical." VOICE: "VOICEOVER (calm, warm, explanatory, American English, mid-30s):" opening clip, full prompt: "An 8-second locked-camera whiteboard explainer, vertical 9:16. Open on a blank white dry-erase board, static tripod shot, no camera movement, no zoom. 00:00-00:05: The hand writes your hook headline in black marker, plain block capitals, upper-left, then underlines it, natural handwriting speed, ink appears stroke by stroke, slight squeak. 00:05-00:08: The hand draws one small icon, upper-right. VOICEOVER: your hook line. AUDIO: marker squeak, quiet room tone underneath. No music. [STYLE LOCK]" every clip after that opens with "use the attached image, [clip N-1]'s final frame, as the opening frame, match the exact board state precisely" before describing the one new action for that beat

80,518 views • 3 months ago

this WHITEBOARD explainer just leveled up. now it's a real person standing at the board, lip-synced, actually writing while she talks her eyes stay on the board the whole time she's mid-stroke, only glancing at the camera between marks. that one detail is what makes it read as a real person teaching something instead of an avatar reciting lines quick workflow: - lock the actor once, straight-on with a blank board, camera perpendicular so nothing keystones - write the dialogue as one continuous script, split into clips with word-for-word timestamps matched to each stroke - a gaze rule keeps her eyes on the board mid-write, camera only between strokes - frame-chain each clip's last frame into the next, lock the board state explicitly so nothing gets redrawn - when chaining voice across clips, lock accent and pitch only, forbid repeating dialogue, or the next clip quietly re-says lines already spoken took a few failed attempts to get the board angle, the gaze, and the voice chaining all working together without breaking each other RT + reply 'BOARD' and i'll send you the full production doc, every prompt, every fix, all of it (must follow so i can DM)

78,765 views • 3 months ago

this YAPPER ad is 100% AI and claude code did 90% of the work all i did by hand was trim the clips it's a rebuild of a real viral organic post: a perfume brand employee ranting in her parked car on her lunch break. what claude code did on its own: - wrote the script with my copywriting skill and swipe library, modelled on the original beat for beat - turned one real frame from the original video into a completely new person in ONE edit - generated 26 Omni takes from that exact frame with her mannerisms copied take by take: the eyebrow raise on the big number, the side eye out the window, palms out for "business mode" - built the edit: stickers, captions, fine print, and the audio matched to a phone mic in a car so it doesn't sound like a studio - checked its own work: camera drift locked, stray words flagged, every take's voice level-matched the one thing i still do myself is the jump cuts. AI cuts on the pause, a human cuts on a blink, and that's what makes it feel real RT + reply 'YAPPER' and i'll send you the full workflow (must follow so i can DM)

29,595 views • 1 month ago

opus 5.5 + google flow is CRACKED this whole JUBILEE style debate ad took about $1 of flow credits and is made entirely by claude code from scratch every talking shot came out of google flow. every frame came out of my ChatGPT. i never opened an editor. approved the frames, gave a few notes on pacing, done how it got built: - claude tore down a reference clip frame by frame - scraped how people actually argue about glp-1s online and wrote the script in their words ("you didn't earn it", "food noise") - turned real show frames into 3 completely new people, one image edit each - every talking shot is omni on google flow - pauses jump-cut out, captions, fine print and end card all done by claude the format works because nobody scrolls past two people arguing. RT + reply 'DEBATE' and i'll send you the full workflow (must follow so i can DM)

opus 5.5 + google flow is CRACKED this whole JUBILEE style debate ad took about $1 of flow credits and is made entirely by claude code from scratch every talking shot came out of google flow. every frame came out of my ChatGPT. i never opened an editor. approved the frames, gave a few notes on pacing, done how it got built: - claude tore down a reference clip frame by frame - scraped how people actually argue about glp-1s online and wrote the script in their words ("you didn't earn it", "food noise") - turned real show frames into 3 completely new people, one image edit each - every talking shot is omni on google flow - pauses jump-cut out, captions, fine print and end card all done by claude the format works because nobody scrolls past two people arguing. RT + reply 'DEBATE' and i'll send you the full workflow (must follow so i can DM)

27,313 views • 1 month ago

the first account i've seen doing EXPLAINER videos with SONGS instead of voiceover 14.3M views on 3 reels. 307K followers off 27 posts it's just a satellite map, one country lit up, and a fun fact... sung why it works: - a song gets replayed. a voiceover doesn't - the melody carries you to the next fact, so you never feel a gap to scroll - the facts rhyme, so they stick (that's how you learned the alphabet btw) - every country gets ~3 seconds, then it's gone every explainer account is fighting for attention with a narrator this one just made it catchy

the first account i've seen doing EXPLAINER videos with SONGS instead of voiceover 14.3M views on 3 reels. 307K followers off 27 posts it's just a satellite map, one country lit up, and a fun fact... sung why it works: - a song gets replayed. a voiceover doesn't - the melody carries you to the next fact, so you never feel a gap to scroll - the facts rhyme, so they stick (that's how you learned the alphabet btw) - every country gets ~3 seconds, then it's gone every explainer account is fighting for attention with a narrator this one just made it catchy

16,455 views • 24 days ago

OPUS 5.5 just made an entire animated ad by itself for $0 no image generation. no video generation. no editing completely one-shotted by OPUS 5.5 inside claude code i tested it on RYZE mushroom coffee with a single prompt, and then i just waited what it did on its own: - researched the product, the audience and the angle - wrote the script and built the storyboard - pulled the real product images straight from the web - produced the voiceover and the captions itself - rendered the finished ad, ready to post you don't need a stack of paid AI tools anymore. opus 5.5 handles the whole production end to end RT + reply 'OPUS' and i'll send you the complete workflow (must follow so i can DM)

OPUS 5.5 just made an entire animated ad by itself for $0 no image generation. no video generation. no editing completely one-shotted by OPUS 5.5 inside claude code i tested it on RYZE mushroom coffee with a single prompt, and then i just waited what it did on its own: - researched the product, the audience and the angle - wrote the script and built the storyboard - pulled the real product images straight from the web - produced the voiceover and the captions itself - rendered the finished ad, ready to post you don't need a stack of paid AI tools anymore. opus 5.5 handles the whole production end to end RT + reply 'OPUS' and i'll send you the complete workflow (must follow so i can DM)

24,737 views • 1 month ago

this entire PODCAST ad was made by claude code for $2 from research, script, video generations, to the final edit made it using my google flow connector so no expensive API credits were used here's what it actually did: - dug through real reviews for the VOC and wrote them into the script - pulled frames from a real podcast set, swapped both hosts - generated 24 talking takes in omni on flow - built the split screen argument, the explainer panels, the b-roll cutaways, captions and end card by itself i approved the script, the frames and the cut, and gave a few notes. that's it RT + reply 'PODCAST' and i'll send you the full workflow (must follow so i can DM)

this entire PODCAST ad was made by claude code for $2 from research, script, video generations, to the final edit made it using my google flow connector so no expensive API credits were used here's what it actually did: - dug through real reviews for the VOC and wrote them into the script - pulled frames from a real podcast set, swapped both hosts - generated 24 talking takes in omni on flow - built the split screen argument, the explainer panels, the b-roll cutaways, captions and end card by itself i approved the script, the frames and the cut, and gave a few notes. that's it RT + reply 'PODCAST' and i'll send you the full workflow (must follow so i can DM)

10,350 views • 18 days ago

a 19th century SCIENCE JOURNAL is out-explaining every ad on my feed took the victorian anatomy style (brass gears, engraved brains, tiny men in top hats) and rebuilt it for a mushroom coffee brand every plate is one step of the mechanism. coffee floods the brain, the gauge hits red, the clockwork stalls at 3pm. then the product rebuilds the machine quick workflow: - 10 plates in Nanobanana Pro, one per beat of the script - Kling 3 animates each plate, and 3 of the joins use end frames so the camera dives into a prop and lands inside the next scene - the narrator is a victorian lecturer i designed in Gemini TTS, every scene trimmed so he never stops talking - Lyria scores it plate by plate, pizzicato into harpsichord hardest part: the first narrator whispered like a nature doc and every scene had 2 seconds of dead air. fixed both before a single video credit got spent RT + reply 'JOURNAL' and i'll send you the full workflow and style prompts (must follow so i can DM)

19,258 views • 1 month ago

the whiteboard ad just became a PIXAR movie holding a pointer stick instead of a marker, same persona, same script, same product the board doesn't come pre-written anymore either. content appears live as she talks, the stick literally leads each word into existence at its tip before the text shows up quick workflow: - locked the same persona as an animated pixar character, same script, same product - built the board as a progressive reveal instead of fully written upfront, synced to the exact line being spoken - frame-chained all 3 clips the same way as the live-action version, last frame becomes the next clip's anchor - locked the voice across clips the same way too, timbre only, dialogue never repeats the one thing that took the most fixing: getting the stick to point at the right spot low on the board. RT + reply 'PIXAR' and i'll send you the full doc, every prompt, every fix (must follow so i can DM)

the whiteboard ad just became a PIXAR movie holding a pointer stick instead of a marker, same persona, same script, same product the board doesn't come pre-written anymore either. content appears live as she talks, the stick literally leads each word into existence at its tip before the text shows up quick workflow: - locked the same persona as an animated pixar character, same script, same product - built the board as a progressive reveal instead of fully written upfront, synced to the exact line being spoken - frame-chained all 3 clips the same way as the live-action version, last frame becomes the next clip's anchor - locked the voice across clips the same way too, timbre only, dialogue never repeats the one thing that took the most fixing: getting the stick to point at the right spot low on the board. RT + reply 'PIXAR' and i'll send you the full doc, every prompt, every fix (must follow so i can DM)

31,092 views • 3 months ago

this ZOMBIE ad cost me only $8.94 i went completely autistic automating the entire process the whole ad was completely built inside claude code no editing whatsoever, it even added the captions on its own all i did was approve the concept and the storyboard and waited what $8.94 got me: - character sheets so all 5 characters stay identical in every shot - a start image for every scene - the full thing animated in SEEDANCE 2.5 - editing and captions, done by claude - music and audio made externally, then mixed in automatically made this for ryze RT + reply 'ZOMBIE' and i'll DM you the framework behind this ad (must follow so i can DM)

this ZOMBIE ad cost me only $8.94 i went completely autistic automating the entire process the whole ad was completely built inside claude code no editing whatsoever, it even added the captions on its own all i did was approve the concept and the storyboard and waited what $8.94 got me: - character sheets so all 5 characters stay identical in every shot - a start image for every scene - the full thing animated in SEEDANCE 2.5 - editing and captions, done by claude - music and audio made externally, then mixed in automatically made this for ryze RT + reply 'ZOMBIE' and i'll DM you the framework behind this ad (must follow so i can DM)

17,562 views • 1 month ago

documentary ads are the most UNDERRATED format in ecom right now this one opens on a real fact: the "coffee break" was a 1952 ad campaign then it moves through the decades. black and white archive photos, then pencil sketches, then modern colour, until the product shows up as the fix quick workflow: - tore down a winning supplement ad frame by frame to steal its structure - 31 nanobanana pro stills with a separate look per decade - only 4 kling clips, the rest are stills with slow push-ins cut to the voiceover - gemini TTS narrator, lyria score, karaoke captions synced word by word RT + reply 'DOCU' and i'll send you the full workflow, every prompt, every fix (must follow so i can DM)

documentary ads are the most UNDERRATED format in ecom right now this one opens on a real fact: the "coffee break" was a 1952 ad campaign then it moves through the decades. black and white archive photos, then pencil sketches, then modern colour, until the product shows up as the fix quick workflow: - tore down a winning supplement ad frame by frame to steal its structure - 31 nanobanana pro stills with a separate look per decade - only 4 kling clips, the rest are stills with slow push-ins cut to the voiceover - gemini TTS narrator, lyria score, karaoke captions synced word by word RT + reply 'DOCU' and i'll send you the full workflow, every prompt, every fix (must follow so i can DM)

16,571 views • 1 month ago

opus 5.5 is CRACKED for ai drama ads pocket fm runs 40 minute story ads that stay live for 4+ months i pulled their 199 longest runners and turned the whole format into a claude skill for ecom products drop a product link and it hands you a 3-6 min drama script, plus every image and seedance prompt to make it what it actually does: - digs through reviews, comments and deal-site threads, then builds a bank of real customer lines so the dialogue sounds like your actual buyer - remixes premises that already ran 100+ days (the secret heir, the family mistake, rejected then chosen) into your buyer's world - every concept runs on life force 8 stakes, so the story holds up even with the product taken out - your product slides in softly once they're already hooked - storyboard first, then paste-ready nanobanana pro stills and seedance 2.5 clips with character lock tested it on RYZE mushroom coffee and wrote a thanksgiving taste-test drama with zero health claims RT + reply 'DRAMA' and i'll send you the skill + the full playbook (must follow so i can DM)

opus 5.5 is CRACKED for ai drama ads pocket fm runs 40 minute story ads that stay live for 4+ months i pulled their 199 longest runners and turned the whole format into a claude skill for ecom products drop a product link and it hands you a 3-6 min drama script, plus every image and seedance prompt to make it what it actually does: - digs through reviews, comments and deal-site threads, then builds a bank of real customer lines so the dialogue sounds like your actual buyer - remixes premises that already ran 100+ days (the secret heir, the family mistake, rejected then chosen) into your buyer's world - every concept runs on life force 8 stakes, so the story holds up even with the product taken out - your product slides in softly once they're already hooked - storyboard first, then paste-ready nanobanana pro stills and seedance 2.5 clips with character lock tested it on RYZE mushroom coffee and wrote a thanksgiving taste-test drama with zero health claims RT + reply 'DRAMA' and i'll send you the skill + the full playbook (must follow so i can DM)

17,218 views • 1 month ago

opus 5.5 is awesome for making COMIC book ads it just directed a 60 second one with a full cast. every character has their own voice. speech bubbles point at the right mouth. words pop in as they're spoken all of it ran inside claude code: - wrote the brief and a 21 panel script on PAS with a named mechanism ("the empty tank") - built character sheets first, then fed them into nanobanana pro so nobody changes faces between panels - cast 6 different elevenlabs voices, even pitched one up to make the 8 year old kid - found each character's mouth on a grid so the bubble tails land exactly right - edited it all by itself. page turns, slams, screen shake, SFX, music scored act by act cost: ~65 credits in images + a few cents of voice no capcut. no editor. no animator RT + reply 'COMIC' and i'll send you the full step by step guide, every prompt, every fix (must follow so i can DM)

opus 5.5 is awesome for making COMIC book ads it just directed a 60 second one with a full cast. every character has their own voice. speech bubbles point at the right mouth. words pop in as they're spoken all of it ran inside claude code: - wrote the brief and a 21 panel script on PAS with a named mechanism ("the empty tank") - built character sheets first, then fed them into nanobanana pro so nobody changes faces between panels - cast 6 different elevenlabs voices, even pitched one up to make the 8 year old kid - found each character's mouth on a grid so the bubble tails land exactly right - edited it all by itself. page turns, slams, screen shake, SFX, music scored act by act cost: ~65 credits in images + a few cents of voice no capcut. no editor. no animator RT + reply 'COMIC' and i'll send you the full step by step guide, every prompt, every fix (must follow so i can DM)

13,918 views • 1 month ago

HOLY SH*T... i just built a full faceless youtube studio inside claude code runs the exact pipeline behind my last video: 29 images, 12 animated clips, AI voice, AI music, a full edit drop the skill into claude code, pick a niche, and it runs the whole channel with you quick workflow: - sets up the project, your API keys and a receipt that logs every cent - finds your niche: your passion pointed at health, wealth, relationships or happiness, ranked by what advertisers pay - researches the story and labels every claim verified, likely or cut - writes the script + storyboard, then a rough cut with the real AI voice before you spend a dollar - one character sheet so your faceless host looks identical in every shot, then the frames and motion - opus 5.5 edits it in code: captions, charts, music, sound, YouTube-ready loudness - QA watches the final cut for mistakes, then it builds the title + thumbnail pair made to get clicked best for: faceless channels, AI content pages, anyone who wants a youtube channel without a camera or an editor RT + reply 'STUDIO' and i'll send you the skill + guide (must follow so i can DM)

HOLY SH*T... i just built a full faceless youtube studio inside claude code runs the exact pipeline behind my last video: 29 images, 12 animated clips, AI voice, AI music, a full edit drop the skill into claude code, pick a niche, and it runs the whole channel with you quick workflow: - sets up the project, your API keys and a receipt that logs every cent - finds your niche: your passion pointed at health, wealth, relationships or happiness, ranked by what advertisers pay - researches the story and labels every claim verified, likely or cut - writes the script + storyboard, then a rough cut with the real AI voice before you spend a dollar - one character sheet so your faceless host looks identical in every shot, then the frames and motion - opus 5.5 edits it in code: captions, charts, music, sound, YouTube-ready loudness - QA watches the final cut for mistakes, then it builds the title + thumbnail pair made to get clicked best for: faceless channels, AI content pages, anyone who wants a youtube channel without a camera or an editor RT + reply 'STUDIO' and i'll send you the skill + guide (must follow so i can DM)

10,137 views • 1 month ago

FABLE 5.1 is f*cking crazy it just automated the most tedious part of making AI UGC ads trained it on my entire ad library, every prompt I've ever used, every script that's ever won now i drop in a competitor's winning ad and it breaks down the hook, the mechanism, the emotional arc, and the exact belief shift making it convert, then rebuilds all of it around my own product: new script, new avatar, same bones that were already working the part that's actually insane: i run this whole thing from my phone no laptop open, no dashboard to babysit. i drop the competitor ad in on my way out the door, go on my walk, and get a notification when the script and avatar are ready for me to approve how it actually finishes without me: > i approve from my phone, one tap, that's the trigger higgsfield MCP picks it up the second i approve and starts generating the actual clips > comes back with variations in podcast, whiteboard, call-in show, SIMPSONS, whatever format the offer needs > my laptop's sitting on my desk the entire time i'm running an entire ad production pipeline from a walk around the block RT + reply 'FABLE' and i'll send you the entire system (must follow so i can DM)

13,738 views • 2 months ago