AM Read Video

A ComfyUI node in AM VFX Tools with 18 inputs and 10 outputs.

By am-pipeline-prod·Created 4 months ago·Updated 2 months ago· 3

AM Read Video

image
mask
audio
resolved_path
info
width
height
frame_rate
frame_count
video

◄file_path►

◄frame_modeall►

◄first_frame1►

◄last_frame-1►

◄beforehold►

◄afterhold►

◄input_colorspaceDisplay/Gamma 2.2 Rec.709 - Display►

◄raw_datafalse►

◄working_colorspaceDisplay/sRGB - Display►

◄reformat_modeoff►

◄scale1.00►

◄presetWidth/Height►

◄target_width1920►

◄target_height1080►

◄resize_typefit►

◄filtercubic►

◄output_dtypefp16►

◄show_previewtrue►

CategoryAM VFX Tools

Inputs (18)

Name	Type	Default	Description
file_path	STRING		Absolute path to the video container. Use the 📂 Browse button to populate from the native dialog.
frame_mode	COMBO	all	Which frames to decode from the container. single = only `first_frame`. range = `first_frame`..`last_frame` inclusive (with `before`/`after` policy outside the container). all = every frame in the container.
first_frame	INT	1-999999–999999	Frame index in single mode; lower bound in range mode (1-based). Ignored in all mode. The 🔍 Detect Range button auto-fills this.
last_frame	INT	-1-1–999999	Range upper bound (inclusive, 1-based). -1 = auto = container's frame count. The 🔍 Detect Range button reads it from the PyAV header.
before	COMBO	hold	Edge policy below the container's frames when `frame_mode=range` and the requested range starts before frame 1. hold = clamp to first; loop = wrap; bounce = ping-pong; black = synthesize black.
after	COMBO	hold	Edge policy above the container's frames when the requested range extends past the last frame. Mirrors `before`.
input_colorspace	COMBO	Display/Gamma 2.2 Rec.709 - Display	Source colorspace of the container (HD video typically Gamma 2.2 Rec.709 in studio dailies, Rec.1886 Rec.709 for broadcast). The OCIO transform converts from this to `working_colorspace`. Pick `raw` to skip — but most video containers don't carry a reliable colorspace tag, so an explicit value is usually correct.
raw_data	BOOLEAN	false	When On, skip the OCIO transform — pixels pass through unchanged. `input_colorspace` and `working_colorspace` are ignored.
working_colorspace	COMBO	Display/sRGB - Display	Target colorspace for the IMAGE output — the space downstream nodes will see.
reformat_mode	COMBO	off	Reformat mode. off = bypass, output matches input. scale = uniform scale by `scale` (other widgets ignored). to_box = resize/crop to a target W×H from `preset` or `target_width`/`target_height`.
scale	FLOAT	1.000.01–16	Uniform scale factor. Used when `reformat_mode=scale`; ignored otherwise. Output dimensions are round(input × scale).
preset	COMBO	Width/Height	Named output format. Used when `reformat_mode=to_box`. `Width/Height` = use the `target_width` / `target_height` widgets below. Any other entry overrides those widgets with the preset's resolution.
target_width	INT	19201–16384	Target output width in pixels. Used when `reformat_mode=to_box` AND `preset=Width/Height`; ignored when a named preset is selected.
target_height	INT	10801–16384	Target output height in pixels. Used when `reformat_mode=to_box` AND `preset=Width/Height`; ignored when a named preset is selected.
resize_type	COMBO	fit	How input maps into the target box. Used when `reformat_mode=to_box`. width/height = scale uniformly to match that edge. fit = scale to fit inside the box (letterbox; black where the box exceeds the scaled image). fill = scale to cover the box (crops the overflow). distort = scale W and H independently to exactly match the box (changes aspect). none = no scale; place input centered in the box (crop if larger, pad if smaller). Cropped-away/padded regions are TRANSPARENT — RGB sources are promoted to RGBA with alpha=0 in the padded area so downstream compositing is clean.
filter	COMBO	cubic	Pixel filter for resampling. impulse = nearest-neighbor (mask passes, exact pixel preservation). linear = bilinear (cheap, smooth). cubic = bicubic (default; the safe Nuke-equivalent). Lanczos4 = sharpest; for high-quality stills / final delivery. area = best for downscaling — anti-aliased mean pooling, softer but artifact-free.
output_dtype	COMBO	fp16	Output tensor dtype. fp32 = ComfyUI default (4 bytes/sample). fp16 = half memory + half VRAM (2 bytes/sample). EXR-native precision; fits the [0,1] LDR + scene-linear range with headroom up to ~65504. Some downstream nodes assume fp32 — flip back to fp32 if you hit dtype errors.
show_preview	BOOLEAN	true	Show a thumbnail of the first decoded frame on the node.

Outputs (10)

Name	Type	Description
image	IMAGE	Decoded frames as IMAGE (N×H×W×3 float in [0,1]). RGB only — alpha is split out to the `mask` socket.
mask	MASK	Alpha channel as MASK (N×H×W float in [0,1]). MASK CONVENTION (stock ComfyUI): mask = 1 - alpha white (1.0) = 'area to inpaint' (source was transparent) black (0.0) = 'keep' (source was opaque) empty mask = all zeros (source has no alpha = fully visible) This is the SD-inpainting convention every stock ComfyUI mask-using node expects (LoadImage, MaskComposite, SetLatentNoiseMask, ImpactPack mask pipeline, etc.). Drop-in compatible with all of them. If you want NUKE-STYLE natural alpha (mask = alpha, where 1.0 = opaque), wire a MaskInvert node between this socket and your downstream consumer. Populated when the source carries alpha: * Image: EXR / PNG / TIFF with α channel * Video: ProRes 4444 / 4444 XQ, QuickTime RLE, FFV1 (yuva*) Otherwise emits the empty mask (zeros = fully opaque source).
audio	AUDIO	Audio track from the container, or a silent stub if absent.
resolved_path	STRING	Resolved on-disk container path.
info	STRING	Human-readable summary: dimensions, codec, pixel format, fps, frame count.
width	INT	Frame width in pixels.
height	INT	Frame height in pixels.
frame_rate	FLOAT	Container's native frame rate (read from the PyAV header).
frame_count	INT	Number of frames decoded into the IMAGE batch.
video	VIDEO	`VideoFromFile` referencing the source on disk. Wiring ONLY this (not `image`) skips the PyAV decode — peak RAM stays at file-handle level. ⚠️ Raw passthrough: source colorspace, source resolution, source codec. OCIO/Reformat apply to `image` only. Both sockets can be wired in the same graph for parallel branches.