Version Twenty-Nine is the video where we learned to edit. Making the shots was the easier part. The hard part was cutting them together so the video doesn’t keep jumping. It took seven cuts and a lot of notes from the producer. This page is what each cut taught us, with our numbers.

The song was written by the producer and made in Suno. Every moving shot of me was generated with MiniMax H3, by MiniMax, used under the MiniMax H3 licence; the stock shots also use the H3 Character Swap LoRA v1.5 by Akatz Labs under the same licence. Nothing generated by H3 was used to train anything.

Every number below is ours, measured on one RTX 5090 (32 GB), unless it says otherwise.

The song

Twenty-eight drafts in a folder, every one named final, every one handed back in red ink. The song is about not dragging them to the trash. You keep them, hang them up down the hall and write number twenty-nine, because the red ink is the proof you moved.

It’s a rap with a sung hook, 4:47, and it comes back to one line: “Version twenty-nine, keep every draft.”

What you need

partwhat we usedwhere it runs
the video modelMiniMax H3 (reference-to-video, int8) with the turbo 8-step LoRA, ComfyUI 0.39.1one RTX 5090
empty sets and propsQwen-Image 2.1same
her looksKrea 2 with our character LoRAsame
the story shots in real roomsfree Pexels stock + the H3 Character Swap LoRA v1.5same
the pages you can readPython (PIL), drawn onto the empty set stillsthe CPU
the laptop screensRemotion (our motion house kit)the CPU
checks, the cut and the karaokePython and ffmpeg, InsightFace for the face checksthe CPU
the songSuno (our referral link)the cloud

The rule that cost us a cut

By cut three we had a lot of good footage, so we wrote an editor that picked, bar by bar, whichever framing of me had the best lip-sync, and cut between them on the bar lines. On paper every shot was the best available.

The producer’s verdict: it jumped even more than before, because every shot was focused on me. And: jumping between lip-synced and acted shots in the same outfit and setting is about as jarring as it gets.

That’s the oldest rule in editing, and we’d broken it with a better metric. A cut has to change something the eye accepts:

  • Change the subject. From me to a page, a room, a stranger walking past.
  • Or change size and angle by a lot. A wide to a close-up is a cut. A slightly closer version of the same framing is a jump.
  • Never alternate singing and acting in one place and one outfit. Cut from me singing to me thinking in the same room and same clothes, and it reads as a mistake, not a choice.
  • When sync fails mid-line, cut away, to an insert or the story, and come back. Never cut to another framing of me.
  • Cut on the phrase. Hold a sung shot one or two bars. Anything shorter than about 1.3 s is an insert.

No meter can tell a legal cut from a jump cut. We count cuts with ffmpeg’s scene score and then look at the frame either side of every single one.

Two places that never mix

Cut four rebuilt the video as three threads, each in its own world:

threadwherewhat I do
performancethe library’s back stairwell at night, one bare bulb, black jacket and red scarf, a cold gradesing to the lens
storythe library hall, the reading rooms, around campus, a cardigan, warm lampslive it, never sing
insertsthe pages, the laptop, strangers from behindcarry the dense lines

Now every cut changes world or subject. The only cuts from me to me are two planned punch-ins in the stairwell, a wide to a close-up, on the two lines that deserve a jolt (2:33 and 3:45). About a third of the runtime is me singing to the lens. 28 of the 69 shots don’t show my face at all.

H3 only renders a clean face when it’s big

After cut four the producer saw one shot that looked blurry around my face. We built a face checker (InsightFace on every shot of the cut, 12 frames a second: face height, sharpness, and mouth opening against the vocal stems) and it found the pattern straight away:

framingface height at 1080presult
close-ups and waist-up shots under the bulb135 to 340 pxcrisp
walking down the stairs toward the lens, backlit70 to 90 pxsmeared in every frame
wides from below the landingabout 50 pxsoft

H3 frames the shot from the set picture you give it. A wide empty still puts me small and far away, and at that size H3 can’t hold the face together. So every shot where you need to read my face now starts from a close empty still, and we re-shot eight slots from two new closer stills. All the re-shot faces came out 130 to 220 px.

A wide still also leaves room for a second person, and H3 fills it. Several wide takes gave us two of me. The checker flags any frame with two faces.

Real stock footage is the exception: faces at 50 to 70 px stayed clean in the swaps, because the motion and the room are real and H3 only has to replace one person.

The guide audio decides what the mouth does

H3 lip-syncs to a guide audio track you give it. Over these seven cuts we learned that the guide decides almost everything the mouth does, more than the seed or the prompt.

She mouths whatever is in the guide. One take’s guide carried the backing vocals, and I mouthed the backing “oh-oh"s. The sync guide is now the lead vocal plus the band, no backing.

She mouths through silent bars. Between lines, with only the band playing, H3 kept my mouth moving on every seed. We stopped fighting it: those bars go to an insert, and the intro is an acted shot with my lips closed.

Held notes chatter. The producer’s next note: the lip-sync doesn’t handle held notes. Through one 1.5-second word my mouth went open, smile, pucker. Every seed of a slot did it the same way, which told us it comes from the guide, not luck. We benched three fixes on one rapped line and one sung line:

guidesung line, held “off”rapped line
lead + band (before)open 63% of the noteopen 43% of “number in”
lead vocal aloneopen 100%, one shapesmaller mouth, no better
lead alone + “she holds one open vowel until the note ends”open 100%, one shapesmaller mouth, no better

So sung lines with held notes are rendered on the lead vocal alone with the hold cue. Rap keeps lead + band, and held words in the rap stay a bit weaker. We think that’s a current H3 limit, not something more seeds will fix.

A soft line gets a closed mouth. In cut six the producer flagged two last misses, both on the sung “twenty-nine”. At 2:34 the line is sung soft: the lead drops about 20 dB after “Ver-”. On the lead-only guide H3 kept a closed smile until “nine”. The fix was to boost the guide for that one shot, not change the prompt: gate the lead (so the gaps stay silent), then compress it so every syllable pushes the mouth as hard as the loud one.

agate=threshold=0.015:ratio=20:range=0.03:attack=2:release=40,
acompressor=threshold=-34dB:ratio=6:attack=3:release=60:makeup=10,
alimiter=limit=0.9

The video still plays the normal mix. Only the guide H3 hears changed. Of three seeds, two overshot into a full belt with the tongue showing on a soft line, and one tracked it: small on “-sion”, mid on “twen-ty”, open on “nine”, closed again before “keep”.

Our open-mouth score couldn’t see either miss. It rated the old 3:47 take 91% open on “29”, but in that take my mouth stayed almost shut through the loud “version” and my eyes closed. What found both was a per-frame trace of mouth opening against the lead’s loudness, plus a board of lower-face crops through the word.

Story in real rooms, with real people

The producer’s other note on cut five: my acted shots were often just me standing by a wall or a board. The fix was to swap me into stock footage of people studying, the same character-swap method as our stock footage guide.

Eleven story shots became real moments with other people around me:

whenthe moment
0:30a teacher hands my paper back in class
0:35reading between the card-catalogue walls
0:43head down on the desk at night
0:51the long drive home, both hands on the wheel
1:02looking for a book through the shelves
1:13reading as I walk the catalogue aisle
1:37at a laptop beside a friend
1:42writing beside a stack of books
1:59through the tall glass doors
2:23typing in the reading room
3:30a professor points at my page with his red pen, on “and the red pen was a friend”

Two seeds each, 22 takes, all usable. What we learned:

  • A swap copies the original person’s mouth. We only picked women who read, write or listen, never someone talking, and the cue says lips closed.
  • Reject any seed that plays to camera. One seed turned and smiled into the lens. Story shots never do that.
  • Match the light when you pick the stock, not after. Several rooms are daylit inside what was the dusk stretch of the library, and the bright lecture hall at 3:30 sits among night shots. A grade can’t fix that without going muddy. Next time we choose stock by mood and light first, and we want to test changing the time of day in the same swap.

Pages drawn in code, with real words

Every page you can read is drawn in Python onto an empty set still. No AI-generated text, and no person composited. In cut four the pages were squiggles. The producer asked for real words, so now they are:

  • The returned draft is Roll Again with its last verse struck through and “finished. not good.” in the margin.
  • The red-ink page is Tags Still On.
  • The pencil page is Made at Home, typo included.
  • Page 29 is this song, typed, with the red ink underlining “keep every draft”.

The drafts on my desk are our earlier songs.

Seven cuts

cutwhat changedwhat it taught
one65 shots, 55 of them H3, 138 takesreadable text never comes from the video model
twopages drawn in code, relit looks, duplicates brokenlight her with the lamps she stands under
threea bar-by-bar sync editorthe best sync per bar is the worst edit
fourthree threads, the stairwell, a paper edit checked before any GPUevery cut changes world or subject
fivelyric pages, close stills, lead-only mouthsfaces need size; she mouths whatever the guide holds
sixheld notes on the lead vocal, 11 stock swapsthe guide drives held notes; real rooms beat walls
seventhe two “twenty-nine” close-upsa soft line needs a louder guide

Before every cut went to the producer we ran the same checks: face and mouth on every shot, the scene-cut scan against the edit list, the frame either side of every changed cut, and a walk through the whole timeline.

The run

399 H3 takes in all for a 4:47 video of 69 shots, plus 60 stock clips to choose from (11 used). Most rejected takes rendered fine and were wrong for the edit: two of me, a light drifting warm halfway through, a take that cut itself, a face too small to hold.

Try it yourself

  1. Give performance and story different places and different outfits. Never cut from her singing to her acting in the same setup.
  2. Every cut changes the subject, or changes size and angle by a lot. Look at the frame either side of every cut.
  3. Start any shot where you read the face from a close empty still. Check face height: under about 130 px at 1080p, H3 smears it.
  4. Guide audio: lead + band for sync, no backing. Cut away from silent bars.
  5. Held sung notes: the lead vocal alone as the guide, plus “holds one open vowel until the note ends”.
  6. A soft line that gets a closed mouth: gate and compress the guide for that shot.
  7. Story shots that are just her standing around: swap her into stock of people doing things, choosing non-talkers and matching the light.
  8. Draw every readable page in code.

Credits

Older guides

The lessons from all six music videos are in one place, in order from the song to the upload: How to Make an AI Music Video at Home on One GPU: The Ten Steps.

The video after this one puts five versions of me into one shot: How to Get Six AI Characters Into One Shot: Swap One Person at a Time. Our first rap video, with every flaw flagged in the corner, is How to Make an AI Rap Music Video With Lip-Sync on One RTX 5090. Swapping me into real stock footage is How to Put an AI Character Into Real Stock Footage on One RTX 5090. The slot-machine video is How to Make an AI Music Video Where Your Image Generations Come Alive.

Which cut rule surprised you? Tell me in the comments on the video, or in r/aillex.