Sep 14, 2026 · Free Guide

“EDIT” Two AIs Edited the Same Video. Here Are Both Prompts, Both Style Guides and Both Full Videos

I've never opened a video editor. This video got edited twice, by two different AIs, from one prompt each, in about 20 minutes. No timeline, no keyframes, no me. Below is everything I sent them and everything they sent back, so you can run the same play on your own recording tonight.

Watch both edits

Same recording. Same audio. Zero human edits after the prompt. One model went editorial and lime. The other went brand orange and loud. Neither one touched my face, and both put the graphics on the exact words I said.

GPT-6 ASTRA
CLAUDE FABLE 5.1
THE REEL I POSTED

What I actually did

One phone recording, already trimmed to 27 seconds. Then the same brief to both models: keep my 9:16 video in the middle, fill the space on each side with animated graphics that illustrate what I'm saying, add word-synced captions, add sound effects, render at 1920 x 1080.

The toolkit was the same for both:

  • HyperFrames for the composition, the animation, the captions and the sound-effect timing. The edit is an HTML file plus a timeline, rendered in headless Chrome.
  • Seedance 2.5 for a short generated video insert and GPT Image 2.5 Sunburst for image overlays and one made-up “creator reel” frame.
  • Real screenshots of the tools I name in the video, captured by the AI itself with a browser.
  • A reference reel so the model knew the layout I wanted.

Astra ran in Codex. Fable ran in Claude Code. Both finished in roughly 20 minutes of wall-clock time, most of it waiting on Seedance.

How the two models saw the same job

GPT-6 Astra built a magazine.Every beat is a chapter. The left panel carries a numbered label (“03 / HYPERFRAMES”), a giant uppercase headline with one lime word, and a supporting screenshot. The right panel holds the proof: stacked cards, a waveform, a clock, a checklist. A lime progress bar crawls along the bottom so you always know where you are. Captions are small, sentence case, white with a lime keyword. Calm, structured, expensive looking.

Fable 5.1 built my brand.Dark graphite, one orange, Archivo in expanded black weight, everything uppercase. Cards look like app windows: a mini editing timeline, a terminal typing the prompt, a fake browser with the real Remotion and HyperFrames sites, a phone mockup for the reference reel, a comment bubble that types “EDIT”, a follow button that clicks itself. Captions are big karaoke blocks and the active word punches orange. Every card enters with a whoosh, every reveal gets a pop or a click, the timer gets a chime. Louder, punchier, more Instagram.

Neither is wrong. Astra reads better on a desktop. Fable reads better on a phone. Pick the one that matches your audience and steal the prompt.

Beat map: what I said, what each one drew

What I saidGPT-6 Astra showedFable 5.1 showed
“AI is editing my videos”Headline “AI IS EDITING MY VIDEOS.” plus a two-step card: give a prompt, build the visualsA dark editing timeline with a moving playhead, a “FABLE 5.1 is editing” panel on the right
“I pasted this prompt”“PASTE THE PROMPT.” headline, an edit brief card on the rightA terminal window typing the real prompt, character by character
“Remotion to cut the bad takes”“KEEP THE GOOD TAKES.” with the Remotion site, a waveform with takes marked in redReal Remotion screenshot on the left, a clip strip on the right where a blade slices out the bad take
“HyperFrames to add animations”“ADD ANIMATION.” with the HyperFrames site, stacked MOVE / LAYER / ANIMATE cardsHyperFrames site in a fake browser, a GSAP chip, two shapes animating on the right
“Seedance 2.5 or GPT Image 2.5 for overlays”“GIVE IT SOMETHING TO SHOW.” with model chips and a Seedance clipA generation panel rendering a Seedance 2.5 fireball clip, a GPT Image 2.5 clapperboard with an OVERLAY stamp
“Gave it a reference video”“SHOW THE STYLE YOU LIKE.” with a made-up creator frame and a Layout / Timing / Visual language checklistA phone mockup playing a made-up creator reel, a “STYLE” panel that reads Archivo and Plex Mono off it
“About 20 minutes total”Giant lime “20 MINUTES.” and a clock hand sweepingA ring timer counting to 20 MIN, a checklist ticking off Cut, Animations, Overlays, Style match, Captions + SFX
“Videos to pop and engage people”“MAKE IT POP.” with an oversized tilted POP, a “Keep them watching.” cardGiant orange POP, then a heart / comment / share row with +1 counters
“Comment edit”“COMMENT EDIT” with a lime EDIT button, a “THE HOW-TO.” checklistA comment bubble types EDIT, my reply appears, a follow button flips to Following

Your script gets its own beats. Copy the method, not the cards.

STYLE GUIDE

GPT-6 Astra

ElementTreatment
Canvas1920 x 1080, 30 fps, H.264
Video9:16 footage centered at full height, about 608 px wide, no crop, face untouched
PanelsLeft and right, about 50 px of padding, subtle grid texture, hairline borders, restrained shadows
BackgroundDark graphite #11151b
TextWarm white #f3f2ee
AccentLime #cbfa67 for one keyword per headline, active steps and results
Alert colorRed, used once, on the discarded take
FontInter, all weights. Uppercase headlines around 64 px, tracked-out labels at 12 to 14 px
Left panel structureTiny model label top left, chapter label in lime (“03 / HYPERFRAMES”), giant headline, supporting screenshot card, section footer bottom left
Right panel structure“ONE RECORDING. REIMAGINED.” kicker, lime section title, stacked proof cards, the active card fills lime with dark text, “IN PRACTICE” footer
ProgressThin lime bar along the very bottom that grows with the video
CaptionsSentence case, Inter semibold around 28 px, white on a dark translucent plate, keyword in lime, low center over the chest
MotionEase-out entrances 0.3 to 0.5 s, related elements staggered 0.06 to 0.1 s, small overshoots on emphasis, holds so each visual can be read
SoundVoice untouched, quiet clicks and whooshes on reveals, generated clips muted
STYLE GUIDE

Claude Fable 5.1

ElementTreatment
Canvas1920 x 1080, 30 fps, H.264
Video584 x 1038 px card, 21 px from the top, 26 px corner radius, hairline border, deep shadow, soft vignette top and bottom, a 4% settle-in zoom at the open
Side columns556 px each, content vertically centered, 22 px gap between stacked cards
BackgroundNear-black #0E0E10 with a 44 px dot grid and a faint orange glow behind the video
PanelsGraphite #1B1B1E, 1 px #2C2C30 border, 24 px radius, status dot top left, mono label, one orange chip
PaletteOrange #FF5B1F, cream #F4EDE0, ink #151517, muted grey #A9A49C
Orange ruleOne orange hero element per card. Never two
FontsArchivo, expanded width, weight 900 for headlines (64 px big, 34 px h2). IBM Plex Mono for labels, chips and anything that looks like code
Captions3 to 4 words, uppercase, Archivo 900 expanded, 42 px, 28 px word gap, on a dark glass plate 868 px from the top. The active word turns orange and scales to 1.14 with a back-out overshoot in 0.11 s
Card entrance0.3 s, rises 30 px, scale 0.9 to 1, back-out ease, slides in from its own side
Card exit0.2 s fade, slight rise and shrink, hard-killed after so it never flashes
Fake windowsBrowser and terminal chrome with three dots, a URL or file name, dark body, real screenshot inside
Sound effectsShort whoosh on every card entrance, pop on key reveals, key presses under the typing terminal, bass impact on the blade cut and the stamp, soft clicks on checklist ticks, chime when the timer lands, typing plus a ping on the comment reply. All between 25% and 55% of dialogue volume
Generated mediaSeedance 2.5 clip at 720p, 5 s, muted, re-encoded with a keyframe every frame before placing. GPT Image 2.5 Sunburst for the clapperboard and the fictional reference reel
THE PROMPT

The prompt I gave GPT-6 Astra

Paste this into Codex from the folder your video is in. Swap the filename. Swap the three colors if you have a brand.

Edit [VIDEO_FILENAME] in my Downloads folder into a polished 16:9 video. Keep my original vertical recording in the center and build animated graphics on the left and right that illustrate what I’m saying. Use HyperFrames for the composition, animations, captions, and sound-effect timing. Follow the creative direction below. START WITH THE CONTENT Watch and transcribe the entire recording. Break it into meaningful beats based on the spoken ideas. Plan one clear visual treatment for each beat, with graphics appearing when the corresponding idea is mentioned. Preserve my voice, spoken content, and sequence. LAYOUT - Export at 1920 × 1080, 30 fps. - Keep the 9:16 footage centered at full height, approximately 608 pixels wide, preserving its aspect ratio and keeping my face unobstructed. - Use the remaining space as two graphic panels. Leave approximately 50 pixels of padding around each panel’s content. - Put the main idea or a short headline on one side and a supporting diagram, demonstration, screenshot, or visual example on the other. - Place accurate, word-synced captions inside the lower portion of the central video, below my mouth. VISUAL STYLE - Use a dark graphite background (#11151b), warm white text (#f3f2ee), and lime accents (#cbfa67). - Add a subtle grid, fine borders, and restrained shadows for depth. - Use Inter or a similar clean sans-serif. Give each panel a strong focal point, large headlines, short supporting copy, and generous spacing. - Highlight important words, active steps, and results with the accent color. Use red sparingly when illustrating mistakes or discarded material. - Keep all important text readable when the finished video is viewed on a phone. ANIMATION AND VISUAL STORYTELLING - Animate concrete examples of the ideas I mention. For editing, show a timeline being trimmed. For a workflow, reveal connected steps. For saving time, show a clock or duration changing. Choose examples that fit my actual words. - Build visuals progressively: introduce the main object, show the action, then reveal the result. - Use smooth ease-out entrances lasting roughly 0.3–0.5 seconds. Stagger related elements by approximately 0.06–0.1 seconds. - Use small overshoots for emphasis, deliberate directional transitions, and brief holds so each completed visual can be understood. - Keep motion focused. Let supporting elements settle while the main idea is being explained. - Give each visual enough screen time to read, and change scenes at natural boundaries in the speech. ASSETS - Capture real screenshots of websites, products, and tools mentioned in the recording. Use authentic logos and accurate interfaces. - Use Seedance 2.5 for generated video inserts or GPT Image 2.5 Sunburst for image overlays when they strengthen the explanation. - If a requested tool or model is unavailable, tell me before substituting it. - Create original supporting visuals. If a sample creator-video frame is needed, generate a realistic fictional example. AUDIO AND CAPTIONS - Keep my voice clear and natural. - Add subtle clicks, pops, whooshes, or chimes at meaningful animation moments. Keep them quieter than the dialogue and mute generated clips’ audio. - Use high-contrast captions and highlight key spoken words in lime. Keep captions synchronized and clear of my face. DELIVERY Render the complete video and deliver a high-quality MP4 plus the editable HyperFrames project with its assets. Inspect the finished export for text readability, caption accuracy, audio synchronization, missing assets, and overlapping elements.
THE PROMPT

The prompt I gave Fable 5.1

Paste this into Claude Code. Swap the filename and drop in a link to a reel whose layout you like.

Can you edit the video in my downloads folder? [VIDEO_FILENAME].mp4 Basically I want you to transform it into a 16:9 video with animations and overlays on the left and right side of the 9:16 video, similar to how it happens on this video: [REFERENCE_REEL_URL] Use hyperframes for animations and adding sound effects, seedance 2.5 or gpt image 2.5 sunburst for overlays and videos. Make sure to grab screenshots of real things you might need too.

Yes, the Fable prompt is three sentences. Fable pulled the reference reel, transcribed my audio, worked out where my head was from real frames, planned nine beats, captured the screenshots, generated the Seedance clip and the images, wrote the whole composition, fixed its own lint errors, checked the frames and rendered. The long prompt gets you a more predictable look. The short prompt gets you the model's taste. Both work.

HOW TO INSTALL

Install it in two minutes

You need Node.js 22 or newer and FFmpeg. Then tell Claude Code (or Codex):

Install HyperFrames for me and make sure Node 22 is active: https://github.com/heygen-com/hyperframes

Prefer to do it manually? Paste these into your terminal one at a time:

brew install ffmpeg nvm install 22 && nvm use 22 npx hyperframes doctor

If doctor shows green checks for FFmpeg and Chrome, you're ready.

For the generated media, give the agent access to Seedance 2.5 and GPT Image 2.5 Sunburst through whichever generation service you already use. Skip it and the prompt still works, you just won't get the video and image inserts.

Step by step, what happens when you run it

  1. Inspect. Probes the file, pulls frames, figures out where your head sits.
  2. Transcribe. Whisper gives every word a start and end time.
  3. Reference. Downloads the reel you linked and studies the frames.
  4. Plan. Picks the beats. Ask to see the plan before it builds.
  5. Assets. Screenshots the real sites, generates the Seedance clip and the images.
  6. Build. One HTML file: video card, two columns of cards, captions, a timeline, a sound-effect cue sheet.
  7. Check. Lint, snapshots, fixes.
  8. Render. One command. Under a minute for 27 seconds.

All Resources

HyperFrames (GitHub)The free video framework
HyperFrames DocsComposition and render reference
RemotionProgrammatic cutting
Claude CodeWhere Fable ran
CodexWhere Astra ran
Google FontsArchivo, IBM Plex Mono, Inter
The first EDIT guide (9:16)The vertical reel version

The Next Step

Guides show you what. AI Builders shows you how.

Inside the community, I walk through every build live, including the stuff that doesn't make it into guides. Regular people (not developers) figuring out AI together, shipping real projects, asking me anything. No fluff, no theory, just the actual work.

Join AI Builders

skool.com/ten-fold