Single-Subject Tracking + Automatic 9:16 Reframe
Click one person or animal on the preview frame and get back a vertical video that follows only them, with the original audio intact. Runs on the same SAM 3.1 (Video) tracking model as the Video Segmentation node, wrapped as a one-click reframing tool — no masks to handle, no keyframes to set.
📹 See it in action
Input: a wide 4K group dance clip (26 s, 16:9, shown here downscaled to 1280 px)
Output: one click on the dancer in red. Subject Follow kept her framed for the full 26 seconds as a vertical clip, while the two dancers beside her stayed out of the crop.
Settings: Pick Subject at 0.68,0.55 on the frame at 9.2 s · Framing natural · everything else at defaults. Delivered at 1080×1920; shown here at 720 px wide. Build this yourself with the Make a Fancam That Follows One Person card.
What it does
Subject Follow takes a horizontal (or any aspect) video and one click. You pick the person or animal you want on the preview frame; the click is stored as an "x,y" pair of fractions of frame width and height. SAM 3.1 tracks that subject across the clip, and the node converts the track into a moving crop window that keeps the subject framed as the shot moves — then renders a 1080×1920 vertical video with the source audio carried through unchanged.
The difference from the Video Segmentation node is what comes out. Video Segmentation returns per-frame masks and IDs for you to composite with. Subject Follow returns a finished vertical video — the tracking is a means to an end, not the deliverable. Three controls shape the result: who (the picked point), how tight (a framing preset plus a punch-in multiplier), and how the crop is delivered (final 1080×1920, or the crop at its native size for an upscaling node downstream)
Problem it solves
- Horizontal footage → vertical, without an editor – Reframe interviews, webinars, lectures, and podcasts for Shorts / Reels / TikTok without manual keyframing or pan-and-scan work
- Pets and animals, too – Follow a dog, cat, or other animal (or an animated character) for pet clips and wildlife shorts, not just people
- Keeps one person centered in a crowded frame – A single click isolates the subject; other people in shot don't pull the crop around
- Audio survives the reframe – The source audio track is preserved, so the clip is publishable as-is rather than needing a re-marry in an editor
- Consistent framing across a batch – The same preset (
full_body,upper_body,face) applied over many clips produces a uniform look, which manual cropping does not - Feeds an upscaling step cleanly –
nativeoutput hands the raw crop to a super-resolution node instead of baking in an upscale the node didn't optimize - Cheaper than full multi-object segmentation – One subject, one track; no mask assets to store or post-process
Input/Output
- Input: Video clip + one subject point
- Format: Standard video formats (MP4, MOV, etc.)
- Subject point: Click on the preview frame via Pick Subject. Stored as
"x,y"fractions of frame width and height - Subject type: A person or an animal (animated characters also work). People are searched for first; animals are searched for only when no person is found. If people are on screen, a click on an animal follows the nearest person instead — use clips where the animal is the only subject
- Prompt type: Visual (point) only — this node does not take a text concept prompt. Use the Video Segmentation node for language-prompted selection
- Options:
- Pick Subject (button) — opens the preview frame; click the person or animal to follow. Stored as
"x,y"fractions of width and height - Framing (dropdown) — how tightly to frame the subject.
naturalkeeps the original size; the others punch in until the subject fills the frame that much natural(default) ·full_body·upper_body·face- Punch-in (slider,
1–4in steps of0.1, default1) — punch-in on the subject.1keeps the natural size; higher values crop tighter and enlarge more. At4the crop is a quarter of its natural width, so the subject fills the frame but the source pixels are stretched four times further - Tracker sampling rate (slider,
1–15in steps of0.5, default5) — how often the tracker looks. Higher follows fast movement more closely and costs more GPU time. Raise it for handheld or fast-moving subjects; lower it for a locked-off interview shot - Tracker input width (slider,
480–1920px in steps of60, default960, i.e. the midpoint) — width the tracker sees, in pixels. The crop is always taken from the full-resolution source, so this trades tracking cost against tracking precision, not output sharpness - Output size (dropdown, default
delivered) — deliver the finished 1080×1920 vertical video, or the crop at its own size for an upscaling node to enlarge delivered(default) ·native
- Output: A single vertical video following the picked subject
delivered: 1080×1920 vertical videonative: the crop at its own resolution, intended as input to an upscaling node- Audio: source audio track preserved
- No masks, IDs, or per-frame confidence scores are returned — use the Video Segmentation node if you need those
Performance
The figures below are for the underlying SAM 3.1 (Video) model. This node has not been separately benchmarked end to end; total runtime also includes crop computation and video encode.
Tracking inference time | ~1 – 3 minutes per 200 frames on typical hardware (SAM 3.1 Video) |
Objects tracked | 1 — the picked subject (person or animal). Object Multiplex multi-object scaling does not apply to this node |
VOS benchmarks | SAM 3.1 improved on 6 of 7 standard Video Object Segmentation benchmarks vs. SAM 3 |
Tracking robustness | Persistent subject identity across frames, including under occlusion (inherited from SAM 3.1) |
Cost driver | Tracker sampling rate — raising it increases GPU time roughly in proportion to how often the tracker runs |
End-to-end node timing | Not yet measured — verify on your own footage before committing to a batch schedule |
Model Source
- Huggingface
- License: Custom (SAM License)
- Important: You are not the target of Trade Controls and your use of SAM Materials must comply with Trade Controls. You agree not to use, or permit others to use, SAM Materials for any activities subject to the International Traffic in Arms Regulations (ITAR) or end uses prohibited by Trade Controls, including those related to military or warfare purposes, nuclear industries or applications, espionage, or the development or use of guns or illegal weapon.
Compliance & Provenance
Provider | Meta (open) |
Provider type | Specialized |
License | |
EU AI Act risk class | Minimal Risk |
Art. 50 transparency | Not applicable |
Region availability | Available globally |
Training data summary |
For more on how we classify models and mark outputs, see our AI Policy.
How Subject Follow compares
CNAPS Studio has two video segmentation nodes built on SAM 3.1.
Model | Best for | Notes |
SAM3.1 (Video) | Track every instance of a text concept through a video | Masks per object; ~1–3 min per 200 frames |
Subject Follow | Follow one person or animal you click, as a vertical crop | Built on SAM3.1 (Video); keeps length and audio |
Rough guidance: SAM3.1 (Video) when you need masks for editing or analysis, Subject Follow when you want a ready-to-post vertical video. The Make a Fancam That Follows One Person card uses Subject Follow. Scope notes come from each node's own documentation; the models have not been benchmarked against each other inside CNAPS Studio.
All of these run inside CNAPS Studio — compare them side-by-side.
Run it now
Click to try Subject Follow free
Or start from a ready-made card: Make a Fancam That Follows One Person

