video-continuation

Here are 4 public repositories matching this topic...

ZenHG / ComfyUI-H3-Latent-Relay

ComfyUI nodes for MiniMax-H3 multi-segment video: seamless continuation via a latent bridge (previous segment's AV latent pinned into the next segment's conditioning) — zero re-encoding. | MiniMax-H3 多段续接 latent 桥：上一段 AV latent 钉进本段 conditioning，零重编码，长视频不漂。

python h3 minimax video-generation latent-space text-to-video multi-segment generative-ai ai-video comfyui long-video comfyui-nodes comfyui-custom-nodes minimax-h3 video-continuation latent-bridge

Updated Oct 26, 2026
Python

supElement / ComfyUI_MinimaxH3_AutoContext

Star

A long video generation solution that breaks through the memory barrier: automatic segmented inference + inter-segment Latent anchoring, allowing MiniMax H3 to generate infinitely continuous long videos with limited video memory.

comfyui minimax-h3 minimax-h3-longvideo video-generated-in-segments video-continuation video-backwards dual-video-transition latent-cache seamless-segmented-reasoning

Updated Nov 6, 2026
Python

yjrocks712 / H3-Seamless

Star

MiniMax H3 video continuation for Wan2GP. Watch the native reframe disappear, then see a 40-second, 3-window result. Overlap replay, bounded video state, real before/after demos, and the full method.