ComfyUI Video Joiner: Troubleshooting Frame Generation

Hey there, fellow ComfyUI enthusiasts! It sounds like you've run into a bit of a head-scratcher with the ComfyUI-Wan-VACE-Video-Joiner workflow, where instead of seamlessly stitching your clips together, it's only spitting out individual frames from the first clip. Don't worry, this is a common hiccup when you're getting started, especially with powerful tools like ComfyUI and the innovative VACE nodes. We've all been there, staring at a folder full of JPEGs when we were expecting a beautiful, combined video! Let's dive deep into why this might be happening and how we can get your clips joined up the way you intended. Understanding the flow of ComfyUI and how these specialized nodes interact is key, and often, it comes down to a subtle configuration or a misunderstanding of the node's output. We'll break down the common culprits and guide you through the troubleshooting process, ensuring you can confidently merge your video creations. So, grab your favorite beverage, settle in, and let's get your videos joined!

Understanding the Core Issue: Why Individual Frames?

The primary reason you're seeing individual frames instead of a joined video often boils down to how the ComfyUI-Wan-VACE-Video-Joiner workflow is interpreting your input and processing the frames. ComfyUI, at its heart, is a node-based system that processes data sequentially. When you're working with video, this data is essentially a series of images (frames) that, when played in sequence, create the illusion of motion. The VACE nodes, and specifically the video joiner component, are designed to take these sequences of frames from multiple sources and combine them into a single output video file. If the workflow isn't correctly set up to assemble these frames into a video after processing, or if there's a misconfiguration in the final output node, it will simply pass through the processed frames it receives, which in this case, are the frames from your first clip.

Think of it like building with LEGOs. You've got two sets of instructions (your clips), and you're trying to combine them. The workflow is supposed to read both sets of instructions, build the first part, then build the second part, and then carefully connect them into one large structure (the video). If something goes wrong, it might just build the first part and hand you all the individual bricks (frames) from that part, forgetting the second part and the crucial step of connecting everything. This can happen for several reasons:

• Incorrect Output Node Configuration: The most common culprit is that the final node responsible for creating the video file (e.g., a Save Video or similar node) might not be properly linked or configured. It needs to receive the sequence of frames from the joiner node and then encode them into a video format (like MP4 or MOV). If it's expecting a different type of input or isn't set up to encode, it might just output the frames it receives raw.
• Data Flow Interruption: There might be a break in the data chain between the video joiner node and the final output node. Even if the joiner is correctly processing and combining the frame data internally, if that combined data isn't successfully passed to the node that renders it into a video file, you’ll end up with just the raw frames.
• Node Version Incompatibility: While less common, it's possible that there's an incompatibility between different versions of ComfyUI, the VACE nodes, or other supporting nodes in your workflow. Sometimes, a newer version of one component might expect data in a slightly different format than an older version of another is providing.
• Input Format Issues: Although you're aiming to join clips, the format or structure of the input clips themselves, or how they are fed into the joiner node, could be causing issues. The joiner expects specific types of input, and if one of the clips isn't formatted correctly, it might cause the processing to halt or default to only handling the first valid input.

By understanding these potential points of failure, we can systematically work through the setup to pinpoint the exact cause. It's all about tracing the data path and ensuring each node is doing what it's supposed to do, in the right order, with the right information.

Common Causes and Solutions

Let's break down the most frequent reasons why your ComfyUI-Wan-VACE-Video-Joiner workflow might be outputting individual frames instead of a cohesive video, and more importantly, how to fix them. This is where we roll up our sleeves and get into the nitty-gritty of your ComfyUI setup.

1. Incorrect Video Saving Configuration

This is, by far, the most common issue. The