SeedVR2ProgressiveSampler - ComfyUI Built-in Node Documentation

Complete documentation for the SeedVR2ProgressiveSampler node in ComfyUI. Learn its inputs, outputs, parameters and usage.

Sequential temporal chunking sampler for SeedVR2 native workflows. This node processes long video latents by splitting them into smaller temporal chunks, sampling each chunk sequentially, and blending the results together. It serves as a drop-in replacement for the standard KSampler when working with SeedVR2 models on sequences that would otherwise cause out-of-memory errors.

Inputs

Parameter	Description	Data Type	Required	Range
model	The model used for denoising the input latent	MODEL	Yes
seed	The random seed used for creating the noise (default: 0)	INT	Yes	0 to 0xffffffffffffffff
steps	The number of steps used in the denoising process (default: 20)	INT	Yes	1 to 10000
cfg	The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality (default: 1.0)	FLOAT	Yes	0.0 to 100.0
sampler_name	The algorithm used when sampling, this can affect the quality, speed, and style of the generated output	COMBO	Yes	Multiple options available
scheduler	The scheduler controls how noise is gradually removed to form the image	COMBO	Yes	Multiple options available
positive	The conditioning describing the attributes you want to include in the image	CONDITIONING	Yes
negative	The conditioning describing the attributes you want to exclude from the image	CONDITIONING	Yes
latent	The latent image to denoise	LATENT	Yes
denoise	The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling (default: 1.0)	FLOAT	Yes	0.0 to 1.0
frames_per_chunk	Pixel frames per temporal chunk. Must be a 4n+1 value (1, 5, 9, 13, 17, 21, …) to match SeedVR2 constraints (default: 21)	INT	Yes	1 to 16384 (step of 4)
temporal_overlap	Latent frames blended between adjacent chunks to hide the seam; 0 means no blend (default: 0)	INT	Yes	0 to 16384
chunking_mode	manual = use frames_per_chunk exactly; auto = shrink the chunk until it fits in VRAM (default: “manual”)	COMBO	Yes	”manual" "auto”

Note on frames_per_chunk: This parameter must be a 4n+1 pixel-frame count (1, 5, 9, 13, 17, 21, …). The node will raise an error if an invalid value is provided.

Note on temporal_overlap: The overlap value is automatically capped to be at most one less than the latent chunk size to ensure valid chunk processing.

Note on chunking_mode: When set to “auto”, the node will automatically try smaller chunk sizes if the current chunk causes an out-of-memory error. If all attempts fail, the node raises an error.

Outputs

Output Name	Description	Data Type
latent	The denoised latent output, concatenated from all temporal chunks back into a single collapsed SeedVR2 latent tensor	LATENT

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): a4574c3e619954b5569551b5b2ba112ecbff918dcebb5ba718a14e77701144a9