Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-MiniMax-H3-LongMedia > MiniMax H3 • Stitch Continuation

ComfyUI Node: MiniMax H3 • Stitch Continuation

Class Name

MiniMaxH3LatentLabStitchContinuation

Category
MiniMax H3/LongMedia/Continuation
Author
vizart-vj (Account age: 2338days)
Extension
ComfyUI-MiniMax-H3-LongMedia
Latest Updated
2026-08-12
Github Stars
0.02K

How to Install ComfyUI-MiniMax-H3-LongMedia

Install this extension via the ComfyUI Manager by searching for ComfyUI-MiniMax-H3-LongMedia
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-MiniMax-H3-LongMedia in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

MiniMax H3 • Stitch Continuation Description

Seamlessly integrate audiovisual latent data segments with smooth transitions for continuous flow.

MiniMax H3 • Stitch Continuation:

The MiniMaxH3LatentLabStitchContinuation node is designed to seamlessly integrate segments of audiovisual (AV) latent data by removing overlaps between consecutive segments. This node is particularly useful in scenarios where you need to create a continuous flow of AV content from separate segments, ensuring that the transition between these segments is smooth and without noticeable interruptions. By leveraging the stitch continuation method, this node effectively synchronizes the tail of a previous AV result with the opening of a new segment, thus maintaining the coherence and fluidity of the audiovisual experience. This capability is essential for AI artists who aim to produce long-form media content with consistent quality and seamless transitions.

MiniMax H3 • Stitch Continuation Input Parameters:

source_av

The source_av parameter represents the initial latent audiovisual data that serves as the starting point for the continuation process. It is crucial for defining the base content that will be extended and stitched with subsequent segments. This parameter is of type LATENT, indicating that it deals with latent representations of audiovisual data.

length

The length parameter specifies the duration of the continuation segment in terms of frames. It determines how long the new segment will be and directly impacts the overall length of the final stitched content. The value is an integer with a default of 124, a minimum of 5, and a maximum of 3600, with increments of 17. This parameter allows you to control the temporal extent of the continuation.

overlap_frames

The overlap_frames parameter defines the number of frames that will overlap between the previous segment and the new continuation segment. This overlap is essential for creating a smooth transition between segments. The value is an integer with a default of 22, a minimum of 5, and a maximum of 3600, with increments of 17. The overlap is snapped down to the 17*k+5 H3 grid, ensuring alignment with the underlying grid structure.

video_context_denoise

The video_context_denoise parameter controls the level of denoising applied to the video context during the continuation process. It is a float value ranging from 0.0 to 1.0, with a default of 0.0. This parameter allows you to adjust the balance between preserving original video details and reducing noise, which can be particularly useful in maintaining visual quality across segments.

audio_context_denoise

The audio_context_denoise parameter functions similarly to video_context_denoise, but it applies to the audio context. It is a float value ranging from 0.0 to 1.0, with a default of 0.0. This parameter helps in managing the audio quality by controlling the amount of denoising, ensuring that the audio remains clear and consistent throughout the stitched segments.

MiniMax H3 • Stitch Continuation Output Parameters:

continuation_av

The continuation_av output represents the newly created latent audiovisual data that results from the stitching process. This output is crucial as it forms the basis for the next segment in the sequence, ensuring continuity and coherence in the audiovisual content.

frame_count

The frame_count output indicates the total number of frames in the continuation segment. This integer value provides insight into the temporal length of the newly created segment, which is essential for planning and synchronizing subsequent segments.

actual_overlap_frames

The actual_overlap_frames output specifies the number of frames that were effectively used for overlapping between segments. This value is important for understanding how much of the previous segment was utilized to create a seamless transition, which can inform adjustments in future stitching processes.

overlap_seconds

The overlap_seconds output converts the actual_overlap_frames into seconds, providing a more intuitive understanding of the overlap duration. This float value helps in assessing the temporal impact of the overlap on the overall audiovisual experience.

MiniMax H3 • Stitch Continuation Usage Tips:

  • Ensure that the overlap_frames parameter is set appropriately to achieve smooth transitions between segments. A higher overlap may result in more seamless continuity but could also increase processing time.
  • Adjust the video_context_denoise and audio_context_denoise parameters to balance between noise reduction and detail preservation, depending on the quality of the input AV data.

MiniMax H3 • Stitch Continuation Common Errors and Solutions:

"Invalid overlap_frames value"

  • Explanation: The overlap_frames value does not align with the required 17*k+5 grid.
  • Solution: Adjust the overlap_frames value to ensure it fits the 17*k+5 grid pattern.

"Source AV data missing"

  • Explanation: The source_av parameter is not provided or is invalid.
  • Solution: Ensure that valid latent audiovisual data is supplied to the source_av parameter.

"Denoise parameter out of range"

  • Explanation: The video_context_denoise or audio_context_denoise value is outside the allowed range of 0.0 to 1.0.
  • Solution: Adjust the denoise parameters to be within the specified range.

MiniMax H3 • Stitch Continuation Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-MiniMax-H3-LongMedia
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

MiniMax H3 • Stitch Continuation