ComfyUI: Configure sampling and window settings for long video generation

ComfyUI Try it →Watch full video →Olares · May 2026

Demo summary

The user walks through the Wan Video Wrapper sampling node, explaining how to set frame window size, motion frame overlap, and start steps for consistent video generation.

Step-by-step

Locate the sampling section in the Wan Video Wrapper node
Set the Frame Window Size to a value that is a multiple of 4 + 1 (e.g., 33 or 77)
Adjust the Motion Frame Overlap to 9 or higher
Set the Start Step to 0 for image-to-video generation
Increase the Start Step to 2 or 3 for video-to-video generation
Click Run

Options

Increase overlap to 25 for greater smoothness
Leave most settings at their default values

Watch out for

Window size value must always be a multiple of 4 + 1
Setting overlap below 9 results in noticeable choppiness
Increasing overlap value will extend generation time
For video input, you must increase start step to 2 or 3 to maintain consistency

Tips

Use 33 or 77 as ideal window size values
Keep the overlap frame number at 9 for a balance of speed and quality

Highlights

“the sampling section provided by One Video Wrapper is a bit more complex, though most settings can be left at their defaults”

All demos from “Audio-Driven Lip Sync with Infinite Talk | ComfyUI Tutorial S04 P07”

0:510:36Configure Infinite Talk and Wan 2.1 models in ComfyUIThe user demonstrates loading the Infinite Talk model alongside the Wan 2.1 I2V 14B model within ComfyUI, including enabling block swap and torch compile for VRAM optimization.ComfyUI· AI Animation Generator
1:270:23Process audio and images for lip syncThe demonstration shows uploading a character image and using Wav2Vec nodes to extract alignment data from an audio file to generate lip movement instructions.ComfyUI· AI Lip Sync Generator
1:551:13Configure sampling and window settings for long video generationCurrentThe user walks through the Wan Video Wrapper sampling node, explaining how to set frame window size, motion frame overlap, and start steps for consistent video generation.ComfyUI· AI Animation Generator
3:080:30Review Infinite Talk lip sync outputThe video shows the final rendered output where a character's lip movements are precisely synced to the input audio, followed by natural movement back to the original pose.ComfyUI· AI Lip Sync Generator
Watch “Audio-Driven Lip Sync with Infinite Talk | ComfyUI Tutorial S04 P07” →

AI Animation Generator

2:070:23Load Wan 2.2 Animate workflow and install nodesThe user demonstrates how to drag and drop the Wan 2.2 Animate workflow into ComfyUI and use the Manager to install missing custom nodes.MDMZ
2:551:05Configure video input and output settingsThe demo shows how to upload a source video to ComfyUI, set the frame count, and adjust the output dimensions to match the original aspect ratio.MDMZ
16:361:56Setting up HunyuanVideo 1.5 in ComfyUIThe video demonstrates how to update ComfyUI and import the HunyuanVideo 1.5 JSON workflow files to create a node-based generation environment.AI Search
20:151:53Text-to-Video generation in ComfyUIA step-by-step demo of configuring the Hunyuan nodes in ComfyUI, entering a prompt for a 'giant cat', and rendering the final 720p video.AI Search
29:151:33Running HunyuanVideo with GGUF (Low VRAM)The video shows how to use the GGUF loader node to run a compressed version of HunyuanVideo 1.5, enabling video generation on GPUs with as little as 6GB of VRAM.AI Search
0:594:52Configure LTX 2.3 in ComfyUIThe creator walks through the ComfyUI node setup for LTX 2.3, explaining the GGUF model loader, VAE settings, and how to adjust resolution and frame counts for optimal rendering.AIKnowledge2Go
1:230:41Setting up LTX-2.3 in ComfyUIThe creator demonstrates how to browse templates in ComfyUI, search for LTX 2.3, and download the required missing models for the text-to-video workflow.MDMZ
13:071:21Applying LoRA to Wan 2.2 video generationThe video shows how to integrate a LoRA (Low-Rank Adaptation) into a Wan 2.2 workflow to achieve specific cinematic movements like a face zoom.pixaroma
31:133:44Text-to-video with LTX-2The video walks through setting up the LTX-2 model in ComfyUI to generate high-resolution video clips from text prompts and images.pixaroma
39:075:27Cloud-based ComfyUI on RunPod/RunHubThe video shows how to run complex video workflows in the cloud using RunHub AI, demonstrating the interface and execution of InfiniteTalk and Wan 2.2 without local hardware.pixaroma
2:351:46Configure Infinite Talk models in ComfyUIThe creator demonstrates how to organize the necessary models within the ComfyUI workflow, including the Lightning LoRA, quantized Infinite Talk UNET models, and the Wan 2.1 VAE and Clip Vision nodes.Aiconomist
11:060:26Combining audio, images, and promptsA demonstration of layering a specific action prompt (patting stomach) over a specific audio timestamp to create a fully directed AI scene.What Dreams Cost