Theo

I help brands distribute their content ;)

[Theo @theoardley]

https://t.co/ggwUCtMQuO

[Theo @theoardley]

@jenishtalaviya Fixing asap!

[Theo @theoardley]

Fable 5.2 vs Opus 5.5: a paper pop-up book of the 7 Wonders

same prompt, one round of notes each, every page drawn in code (NOT one photo)

Opus on the left, Fable on the right

who did it better, Opus or Fable?

[Theo @theoardley]

@sasoroiko check my website on bio

[Theo @theoardley]

https://t.co/ggwUCtMQuO

[Theo @theoardley]

38M views in 12 days on an AI Short about a custard apple orchard

EASIEST FORMATS TO MAKE WITH FABLE 5.2

the channel's 76 other Shorts sit at a median of about 5.5K. next best: 1.1M

a village couple grows custard apples from seed, picks them and packs the crates (NO voiceover)

[Theo @theoardley]

@novaldzky Got flagged, check my website in bio.

[Theo @theoardley]

Most valuable article of 2026?

[Theo @theoardley]

https://t.co/ggwUCtMQuO

[Theo @theoardley]

a man shut himself inside a wooden crate and mailed it to Australia (true story, 1964)

Fable 5.2 made this whole Short from the prompt in the post below. i gave it the story and told it to keep going on its own

-> it checked the story against its sources and fixed my first line
-> it built the crate, the plane and the shed in Blender
-> it logged 9 fixes to its own work before i saw anything
-> then i had 6 shots redone after a review
-> the voice is a paid one this time, the prompt's own is free

5 changes i made to the prompt first (add them to urs):
-> captions in sentence case, NEVER all caps
-> the person in frame 1, close enough to read on a phone
-> never animate the lens. a smash zoom is a fast dolly
-> a short far clip on ground shots
-> light fog and bloom, a closer camera on near-empty sky shots

the full prompt is in the post below

bookmark this before ur next Short

[Theo @theoardley]

255M views on a 3D Short by Zack D. Films

i tried to rebuild his style with ONE Claude prompt, then ran it on Opus 5.5 and Fable 5.2 (they did NOT make the same Short)

the full prompt is below ↓

paste it into Claude Code in an empty folder and answer its 2 questions. it shows u the script and waits for ur go. u need Blender + its free MPFB add-on and a graphics card. give it a few hours (the prompt is minus one optional paid-voice line)

<inputs>
Ask me 2 things, then wait:
1. The story in one line: a strange TRUE event where one person did one odd physical thing ("He tied 42 weather balloons to a lawn chair."). If I say "you pick", pitch 3 with one source link each and take the first unless I choose.
2. The voice. Default: Kokoro (free, runs on my computer), a calm, warm male narrator.
Then tell me everything else is free: Blender (find my install, or tell me the one download), its free MPFB extension for human bodies (ask me before you install it) and into this folder a Python venv with FFmpeg (imageio-ffmpeg), kokoro-onnx + its model files (kokoro-v1.0.onnx and voices-v1.0.bin from the kokoro-onnx GitHub releases), faster-whisper (small.en), numpy and Pillow. It needs no API key or account and renders on my graphics card with EEVEE.
</inputs>

<direction>
The look: a clean, realistic 3D world, like a good game cutscene. Bright, saturated, a little filmic.
- People: realistic bodies with generic faces and big readable expressions (shock, a smirk, a scream). Plain clothes, no logos. Never a real person's likeness: for a real person keep the face out of close-ups (hands, back, side, distance, straight top-down).
- CALM shots only. Bodies in fast action or contact (running, jumping, fighting, falling) look stiff, so tell the story with frozen moments under a slowly moving camera, macro inserts of hands and objects, rooms, vehicles, the sky, top-down views and the aftermath.
- One new picture for every caption chunk (2-4 words, about 1-1.5 s): a new framing, a new action or a camera move. Nothing ever holds still: every shot drifts, pushes in or orbits.
- The shot kit: macro insert (extreme close-up of the key object or hands, very shallow depth of field), hero low angle (wide lens at waist height), god's-eye top-down with a slow rotate, tracked object, over the shoulder, smash zoom on the word that matters, whip pan between beats, glow highlight (the named object glows orange with a rim, then fades), a big 3D number lying in the scene, a thought bubble (a cloud ring showing what he hoped for), a TV in the scene replaying the event.
- Light: a bright warm sun, blue sky with clouds, soft shadows. Night scenes use hard lamps and a dark sky. Wide lens up close, depth of field on every shot, motion blur on every fast camera move.
- Captions: 2-4 words at a time, white bold rounded sans, about 64 px on a 1080 px-wide frame, centred, 78% down the frame, soft dark shadow, no box. Each chunk replaces the last on the same frame as its picture.
- Banned: real footage, photos, downloaded textures or 3D models, logos, AI images or AI video, downloaded music, gore.
</direction>

<structure>
38-50 s, 100-140 words, 150-180 words a minute. The voice starts at 0.0 s.
- Line 1: the most surprising physical act, in past tense, opening with "He" (or "She"). No name, date or setup. Frame 1 shows that act.
- Then a cause-and-effect chain: every sentence starts with a hinge word (Then, Suddenly, So, Because, But, Later) and is ONE visible action.
- The context arrives late, after "You see,".
- A reveal: someone looks closer and the story turns.
- The last line is the consequence. No call to action, no question.
- Names are rare: use one only when it pays off.
Title = "He ..." or "The Man Who ...". The cover is the first frame.
</structure>

<build>
Save every stage to disk so a crash never costs more than one stage.
- sources.md: every fact with its link and the date you read it. Anything you can't verify stays out.
- script.json: the lines and the caption chunks cut by hand (2-4 words, one picture each), each chunk with its shot: the set, the camera, what moves.
- https://t.co/2ltXAYBEB2: Kokoro reads the whole script in one take (speed 1.0-1.1) and pauses are squeezed to 0.35 s at most; faster-whisper times every word (pass it a 16 kHz numpy array, not a path); write chunks.json with each chunk's start and end. A picture and its caption switch together on frame round(start*30)+1.
- blender/: Python scripts run headless (blender -b -P). https://t.co/Xw0DENaRfo makes one .blend with the sets, the cast, the props and every shot baked with a key on every frame. https://t.co/7dWyuydMpl sets EEVEE with ray tracing, the AgX view with the Punchy look, motion blur, depth of field and bloom in the compositor. Bodies come from MPFB or are built by you; clothes, hair, props and sets are built in code.
- Stills first: one half-size still per shot as a contact sheet. Look at every tile and fix what's off before any full render. Time one full-size frame and tell me the estimate.
- Render 1080x1920 at 30 fps to PNG frames, skipping frames already on disk.
- https://t.co/49eJxversT, numpy only: a light music bed, a sound on every action (a whoosh on each whip pan, hits, wind, room tone), ducked under the voice, mastered to -14 LUFS on the whole stereo mix.
- https://t.co/9GMRkcDO2w: burn the captions in from chunks.json. Encode out/<slug>_9x16.mp4 (1080x1920, 30 fps, TV-range yuv420p) and out/<slug>_x_7x8.mp4 (1008x1152, under 10 MB, 2-pass): a crop of the 9:16 frame that keeps the subject and the caption.
</build>

<gotchas>
- Blender paths: pass absolute output paths (a relative one lands on the drive root).
- MPFB headless: enable it with addon_utils.enable("bl_ext.user_default.mpfb"). Bake a body's shape keys before you pose it: the rig is fitted to the baked shape.
- Clothes: cut them from the body mesh and push them 7-16 mm out along the normals; keep two rings of body faces under every hem.
- Nothing coplanar: keep every resting object 1 cm off its neighbour and draw ground markings into the texture, or they flicker.
- Hair: EEVEE draws hair only from a Curves object, hair type STRIP. Use a Principled BSDF on it (the Hair BSDF renders black).
- Skin: keep subsurface weight near 0.2 (more turns faces black in EEVEE) and add a soft fill light from below under a noon sun.
- Hands: a curled hand reads as a claw from the palm side, so shoot a grip from behind the knuckles.
- Motion blur: shutter position START, a key on every frame, plus a key half a frame after each shot's last frame, so blur never reaches across a cut.
- Check: run a black-frame and one-frame-flicker check on the render. Make a contact sheet (a frame every 0.5 s) and look at every tile: the act reads in the first 2 s, faces are lit, nothing clips through anything, captions stay off faces and key objects. Then step through the first 2 s, the middle and the end frame by frame. Fix, render only the changed shots again.
</gotchas>

<start>
Pitch (or take my story), then show me the script with the word count, the caption chunks with their seconds and the shot list with what the first frame shows. Build nothing until I say go.
</start>

how the two runs went: one run each on the same PC, so it's one sample, not a ranking. both took under 3 hours on one shared 8 GB graphics card. the story for both: a man who tied 42 weather balloons to a lawn chair in 1982

where they split:
-> Opus opened wide on the balloons over the yard. Fable opened on the man kneeling at the chair with his Jeep behind him
-> Opus put 5 big 3D numbers in its scenes, Fable 2
-> Fable followed the caption spec (white text, soft shadow). Opus went ALL CAPS with a thick outline
-> Fable pulled the Smithsonian's own record and ended on the chair in the museum. Opus ended on the $1,500 fine
-> a few Opus shots are hazy and one opens on a blank grey frame

save this for ur next Short. who did it better, Opus or Fable?

[Theo @theoardley]

@picconedoro Overall better too

[Theo @theoardley]

255M views on a 3D Short by Zack D. Films

i tried to rebuild his style with ONE Claude prompt, then ran it on Opus 5.5 and Fable 5.2 (they did NOT make the same Short)

the full prompt is below ↓

paste it into Claude Code in an empty folder and answer its 2 questions. it shows u the script and waits for ur go. u need Blender + its free MPFB add-on and a graphics card. give it a few hours (the prompt is minus one optional paid-voice line)

<inputs>
Ask me 2 things, then wait:
1. The story in one line: a strange TRUE event where one person did one odd physical thing ("He tied 42 weather balloons to a lawn chair."). If I say "you pick", pitch 3 with one source link each and take the first unless I choose.
2. The voice. Default: Kokoro (free, runs on my computer), a calm, warm male narrator.
Then tell me everything else is free: Blender (find my install, or tell me the one download), its free MPFB extension for human bodies (ask me before you install it) and into this folder a Python venv with FFmpeg (imageio-ffmpeg), kokoro-onnx + its model files (kokoro-v1.0.onnx and voices-v1.0.bin from the kokoro-onnx GitHub releases), faster-whisper (small.en), numpy and Pillow. It needs no API key or account and renders on my graphics card with EEVEE.
</inputs>

<direction>
The look: a clean, realistic 3D world, like a good game cutscene. Bright, saturated, a little filmic.
- People: realistic bodies with generic faces and big readable expressions (shock, a smirk, a scream). Plain clothes, no logos. Never a real person's likeness: for a real person keep the face out of close-ups (hands, back, side, distance, straight top-down).
- CALM shots only. Bodies in fast action or contact (running, jumping, fighting, falling) look stiff, so tell the story with frozen moments under a slowly moving camera, macro inserts of hands and objects, rooms, vehicles, the sky, top-down views and the aftermath.
- One new picture for every caption chunk (2-4 words, about 1-1.5 s): a new framing, a new action or a camera move. Nothing ever holds still: every shot drifts, pushes in or orbits.
- The shot kit: macro insert (extreme close-up of the key object or hands, very shallow depth of field), hero low angle (wide lens at waist height), god's-eye top-down with a slow rotate, tracked object, over the shoulder, smash zoom on the word that matters, whip pan between beats, glow highlight (the named object glows orange with a rim, then fades), a big 3D number lying in the scene, a thought bubble (a cloud ring showing what he hoped for), a TV in the scene replaying the event.
- Light: a bright warm sun, blue sky with clouds, soft shadows. Night scenes use hard lamps and a dark sky. Wide lens up close, depth of field on every shot, motion blur on every fast camera move.
- Captions: 2-4 words at a time, white bold rounded sans, about 64 px on a 1080 px-wide frame, centred, 78% down the frame, soft dark shadow, no box. Each chunk replaces the last on the same frame as its picture.
- Banned: real footage, photos, downloaded textures or 3D models, logos, AI images or AI video, downloaded music, gore.
</direction>

<structure>
38-50 s, 100-140 words, 150-180 words a minute. The voice starts at 0.0 s.
- Line 1: the most surprising physical act, in past tense, opening with "He" (or "She"). No name, date or setup. Frame 1 shows that act.
- Then a cause-and-effect chain: every sentence starts with a hinge word (Then, Suddenly, So, Because, But, Later) and is ONE visible action.
- The context arrives late, after "You see,".
- A reveal: someone looks closer and the story turns.
- The last line is the consequence. No call to action, no question.
- Names are rare: use one only when it pays off.
Title = "He ..." or "The Man Who ...". The cover is the first frame.
</structure>

<build>
Save every stage to disk so a crash never costs more than one stage.
- sources.md: every fact with its link and the date you read it. Anything you can't verify stays out.
- script.json: the lines and the caption chunks cut by hand (2-4 words, one picture each), each chunk with its shot: the set, the camera, what moves.
- https://t.co/2ltXAYBEB2: Kokoro reads the whole script in one take (speed 1.0-1.1) and pauses are squeezed to 0.35 s at most; faster-whisper times every word (pass it a 16 kHz numpy array, not a path); write chunks.json with each chunk's start and end. A picture and its caption switch together on frame round(start*30)+1.
- blender/: Python scripts run headless (blender -b -P). https://t.co/Xw0DENaRfo makes one .blend with the sets, the cast, the props and every shot baked with a key on every frame. https://t.co/7dWyuydMpl sets EEVEE with ray tracing, the AgX view with the Punchy look, motion blur, depth of field and bloom in the compositor. Bodies come from MPFB or are built by you; clothes, hair, props and sets are built in code.
- Stills first: one half-size still per shot as a contact sheet. Look at every tile and fix what's off before any full render. Time one full-size frame and tell me the estimate.
- Render 1080x1920 at 30 fps to PNG frames, skipping frames already on disk.
- https://t.co/49eJxversT, numpy only: a light music bed, a sound on every action (a whoosh on each whip pan, hits, wind, room tone), ducked under the voice, mastered to -14 LUFS on the whole stereo mix.
- https://t.co/9GMRkcDO2w: burn the captions in from chunks.json. Encode out/<slug>_9x16.mp4 (1080x1920, 30 fps, TV-range yuv420p) and out/<slug>_x_7x8.mp4 (1008x1152, under 10 MB, 2-pass): a crop of the 9:16 frame that keeps the subject and the caption.
</build>

<gotchas>
- Blender paths: pass absolute output paths (a relative one lands on the drive root).
- MPFB headless: enable it with addon_utils.enable("bl_ext.user_default.mpfb"). Bake a body's shape keys before you pose it: the rig is fitted to the baked shape.
- Clothes: cut them from the body mesh and push them 7-16 mm out along the normals; keep two rings of body faces under every hem.
- Nothing coplanar: keep every resting object 1 cm off its neighbour and draw ground markings into the texture, or they flicker.
- Hair: EEVEE draws hair only from a Curves object, hair type STRIP. Use a Principled BSDF on it (the Hair BSDF renders black).
- Skin: keep subsurface weight near 0.2 (more turns faces black in EEVEE) and add a soft fill light from below under a noon sun.
- Hands: a curled hand reads as a claw from the palm side, so shoot a grip from behind the knuckles.
- Motion blur: shutter position START, a key on every frame, plus a key half a frame after each shot's last frame, so blur never reaches across a cut.
- Check: run a black-frame and one-frame-flicker check on the render. Make a contact sheet (a frame every 0.5 s) and look at every tile: the act reads in the first 2 s, faces are lit, nothing clips through anything, captions stay off faces and key objects. Then step through the first 2 s, the middle and the end frame by frame. Fix, render only the changed shots again.
</gotchas>

<start>
Pitch (or take my story), then show me the script with the word count, the caption chunks with their seconds and the shot list with what the first frame shows. Build nothing until I say go.
</start>

how the two runs went: one run each on the same PC, so it's one sample, not a ranking. both took under 3 hours on one shared 8 GB graphics card. the story for both: a man who tied 42 weather balloons to a lawn chair in 1982

where they split:
-> Opus opened wide on the balloons over the yard. Fable opened on the man kneeling at the chair with his Jeep behind him
-> Opus put 5 big 3D numbers in its scenes, Fable 2
-> Fable followed the caption spec (white text, soft shadow). Opus went ALL CAPS with a thick outline
-> Fable pulled the Smithsonian's own record and ended on the chair in the museum. Opus ended on the $1,500 fine
-> a few Opus shots are hazy and one opens on a blank grey frame

save this for ur next Short. who did it better, Opus or Fable?

[Theo @theoardley]

@_Jaack_Tripper Yeah I made a seperate website, link in bio

[Finn @finnardley]

the amount of people on X copying my posts 1:1 the last 2 weeks has been insane

i dont mind using my concepts and taking inspo, but using my wording 1:1 is NOT okay

is originality this scarce nowadays?

[Theo @theoardley]

TED-Ed's 73 "Can you solve the riddle" videos: median 3.6M views

the bridge one alone: 24M

TED-Ed's riddles run 3 to 5 minutes. so i made a free Claude skill that makes the 60-second version (the Wonderland one below came out of it)

-> Claude writes a riddle nobody has seen
-> it PROVES there's exactly one answer before anything gets drawn (a checker tries every possible world)
-> then animates it as a 45-60 s vertical Short, every frame drawn in code
-> clues pop on the word they're spoken, "pause now and solve it", then the answer step by step
-> free voice on ur own computer, music and sound made in code

u only need Claude Code (nothing else to sign up for)

should i give this away for free?

save this for ur next Short. which riddle should i run through it next?

[Theo @theoardley]

@xboyultimate1 ❤️

[Theo @theoardley]

2.8M views in 5 days on a 30-second AI Potato Fry

every ingredient is a tiny character on a rope swing. it jumps into the pan on cue

5 of the page's 15 Shorts passed 500K (Semiya Payasam: 3.2M)

a 2nd page put Maggi on the SAME swings: 637K (its median: 560)

[Theo @theoardley]

2.3M views on a cartoon Short called "How to Survive a Superintelligence!"

the same channel's 25 other Shorts: median 5.5K

its 8 "How to Survive" Shorts: median 478K (that's 87x)

-> Superintelligence: 2.3M
-> AI Drone Swarms: 1M
-> Superintelligence Part 2: 774K
-> Superintelligence Part 3: 511K (2 days old)

its "What if" Shorts: 70K and 43K

how Part 2 opens (the video below):

-> frame 1: the threat in big caps ("if superintelligence builds a robot army")

-> then an order that sounds wrong: "don't run"

-> then the plan plays out one scene at a time, so u stay to see if it works

"how to survive" makes the viewer the main character AND promises a plan

the topic carries on its own too: Segment Zero's "AI Refuses to Shut Down" Short got 2.1M (that channel's median: 190K)

take the scariest AI headline of the week: title it How to Survive + that thing, put the threat on frame 1 and give an order that sounds WRONG

save this before ur next title

[Theo @theoardley]

@iancccho Worst video gen ever

[𝓚𝓪𝓲 @Kaigrowth]

If you want to become the best version of yourself with minimal effort

bookmark the article below

[Theo @theoardley]

@finnardley @diorscales Not for now, I can make one if theres ppl interested

[Theo @theoardley]

3 AI fairy tales in a row: 286K, 65K and 44K views

the same channel's 11 films from the 3 weeks before: 129 to 1.1K (surreal creature stories)

only the story changed

a story everyone knows by heart makes the dark twist land (u already know how it SHOULD end)

how to copy it:

-> pick a tale people learned as kids
-> start from a version that's already dark (the pigs film is based on Roald Dahl's take)
-> keep the beats they expect, turn ONE of them dark
-> build the main set first as a reference picture (the creator's own note: no reference for grandma's house on Red Riding Hood, so it came out "a bit higgly-piggly")
-> keep the title plain: "The Three Little Pigs - AI Short Film"

save this and remake a fairy tale before the copies show up

[Theo @theoardley]

@Classifiedv4 ❤️

[Theo @theoardley]

HOLY F*CK

611K views on a 65-second Short called "The Prisoner Who Ate the Evidence"

its 4 biggest ALL share one title shape:

-> The Prisoner Who Ate the Evidence: 611K
-> The Man Who Bought the Town's Alarm Bell: 116K
-> The Rooster That Caught a Thief: 44K
-> the Alarm Bell story remade in 3D: 29K

and their covers end on the strange act, said flat (HE ATE THE EVIDENCE)

its story Shorts from the same week with other titles: 2.2K, 2.4K and 18.5K. those open with "He..." / "In This City..." / "Why..." and their covers end in ? or ! (SOLD HIS NAME FOR FREEDOM?!)

"He Sold His Name" is a strange act too. what it's missing is the role: a prisoner, a rooster, a man buying a bell (u picture him before u read the rest)

write ur next story title as: The + a role u can picture + Who + the strangest thing they did. then end the cover on that act, no "?!"

save this before ur next title