🖼 S42 CutFlow Image → Clip

The entire S42 CutFlow suite operates on video - IMAGE batches with many frames. But half the things you want to edit are still images: a title card, a generated hero still, a thumbnail. S42CF_ImageToClip is the bridge: it takes a single IMAGE and duplicates it into an N-frame clip, so a still can flow through video nodes that otherwise wouldn't know what to do with it.

What you set

• image - the single frame. One image in, many frames out.
• duration_mode - frames (specify a count) or seconds (specify a duration). Default is seconds, which is the friendlier one.
• frame_count - 48 by default; used in frames mode.
• duration_seconds - 2.0 by default; used in seconds mode. At 24fps, 2 seconds = 48 frames.
• fps - 24 by default, for the seconds→frames math.

Outputs are clip (the still, repeated), frame_count, and info.

Why a node this boring matters

Because stills want to move. The single most common use is feeding a generated image into S42CF_KenBurns - convert the still to a clip first (the KenBurns tooltip literally tells you to: for stills, use ImageToClip first, or it animates a single frame and gets nowhere). The pattern is: image → ImageToClip → KenBurns → a clip that slowly zooms and pans, which is how you turn a flat AI image into something that plays like video.

Other jobs:

• Title cards. Convert a title image to a ~3 second clip (72 frames at 24fps), then let FrameInsert prepend it to your real footage.
• Still backgrounds. Feed a converted still into the LayerComposer's background layer to build a composite around it.
• Loop material. Convert, then LoopBounce a still with subtle motion - ambient background content from a single image.

It's pure frame duplication, so it's instant, CPU-only, and costs nothing in VRAM. The frame_count output keeps the rest of your chain honest about the new duration.

Install

One node in the 53-node S42 CutFlow pack. ComfyUI Manager → search "S42 CutFlow" → Install → restart. Or:

cd ComfyUI/custom_nodes/
git clone https://github.com/GeekyGhost/S42-CutFlow.git
pip install -r S42-CutFlow/requirements.txt

Restart fully; console prints [S42 CutFlow] Loaded 53 total nodes. The pack's only mandatory dependency is OpenCV (opencv-python-headless in the requirements.txt; the README's troubleshooting tells you to install opencv-python if you hit "No module named 'cv2'").

Standing pack note: Geeky Ghost ships S42 CutFlow as a work-in-progress being groomed for LTX Desktop. The utilities core is the stable layer; expanded nodes are the moving parts.