Finish and conform

Download this guide as Markdown (for your AI agent)

Version 1 (2026-10-15): the same steps as this page, with every download’s link and checksum. sha256 702fb304784f2723faf7611b54941fd59e8dd58917b6178b4bc7657dc6198cf6, also in the manifest.

What to match

Each property of the clip and what to match it to
Property	Match it to
Frames	Keep every generated frame and play them 1:1 at the episode’s frame rate (23.976 for most US TV, 25 for PAL titles, 29.97 where stated; `segment.json` shows the rate). Trim the padding off the end. Exception: new footage with its own generated sound stays at 23.976, and is converted to 25 by repeating frames
Size	The pixel size of your Start still (`first-frame.png`). Scale and crop to fill it; never add black bars
4:3 shows	Work at a 4:3 size and deliver at the 4:3 Start-still size. Crop, never squeeze
Sound (a changed shot)	The original sound of your cut shot. The model’s sound is made up, or a copy
Pictures (a changed shot)	The model’s own pictures, trimmed to your shot. Paste-back is only for the crop route, which does it inside its workflow
Sound (new footage)	The clip’s own sound, leveled to the episode (our inserts aim for about −23 LUFS), exactly as long as its picture
Loudness	A changed shot (a swap or a rebuild) keeps the sound as recorded: no loudness change, and no target. Fix a quiet recording by recording again at 100% / 0 dB. New footage is the exception: its own sound is leveled to the episode (about −23 LUFS)
File	H.264 + AAC MP4, at least 5 seconds to submit (1.5 s for a local pack made outside the builder, with extension 0.64.3 or later). A keyframe every second is optional: it makes seeking into the scene faster

The workflows

A changed shot (Swap a person, Rebuild a shot, Rebuild with actors): the finish workflow (seamless-finish.json, download):
- load your generated part in Generated part and your cut shot in The cut source;
- set Scale to the Start still size.
- It keeps your shot’s frame count, plays every frame at its rate, and puts its sound back, padded or trimmed to exactly the picture’s length, at 48 kHz.
New footage (Add new footage): the add-a-scene finish workflow for your episode’s shape (16:9: seamless-add-scene-finish.json, download; 4:3: seamless-add-scene-finish-4x3.json, download). It covers and center-crops to the Start still size, sets the level, and delivers 48 kHz sound exactly as long as the picture.
25 fps (PAL), new footage: replace 5.160 with the new frame count ÷ 25 (124 frames become 129).
New footage to 25 fps (ffmpeg)
```
ffmpeg -i finished.mp4 -vf fps=25 -af "aresample=48000,atrim=end=5.160,apad=whole_dur=5.160" -c:a aac -ar 48000 finished25.mp4
```

Optional ffmpeg for a keyframe every second, joining parts, or 29.97 film (replace N with your part’s frame count):

One part: trim, re-time 1:1, keyframe every second, the source’s sound (ffmpeg)

ffmpeg -i part1.mp4 -i src.mp4 -filter_complex "[0:v]trim=end_frame=N,setpts=N/(24000/1001)/TB,scale=1280:720:flags=lanczos,setsar=1[v]" -map "[v]" -map 1:a -af apad -r 24000/1001 -c:v libx264 -crf 17 -pix_fmt yuv420p -g 24 -keyint_min 24 -sc_threshold 0 -c:a aac -b:a 192k -shortest swap.mp4

29.97 film (ffmpeg)

ffmpeg -i swap.mp4 -vf fps=30000/1001 -c:v libx264 -crf 17 -pix_fmt yuv420p -g 30 -keyint_min 30 -sc_threshold 0 -c:a copy swap-2997.mp4

Joining pieces

Every piece the same size: a join resizes everything to the first piece.
Each piece’s sound exactly as long as its picture: sounds add up end to end, so 24 ms extra per piece put a later scene’s sound 72 ms late in our test.