←Back to NewsAI News/VideomodelVideoOpen SourceAlibaba's MiniMax-H3-Fun-Controlnet-Union Steers Video Generation With One 6.8 GB CheckpointAlibaba PAI drops a single ControlNet-Union checkpoint that adds Canny, Depth, HED, MLSD, Pose and inpainting to MiniMax-H3 video generation.SourceAlphaSignalPublishedAug 24, 2026, 3:18 AMAuthorAlphaSignal NewsroomRead1 min readAlibaba PAI drops a single ControlNet-Union checkpoint that adds Canny, Depth, HED, MLSD, Pose and inpainting to MiniMax-H3 video generation.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · repoCozyClay Lets You Direct AI Video Shots in 3D Without Writing PromptsAlphaSignal · modelUC Berkeley's VDN-H3 Generates 14-Second Videos Faster Than You Can WatchAlphaSignal · modelCommunity LoRA Sharpens MiniMax H3 Videos Without Hosted 2K API