Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.
LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler has 499 GitHub stars.
It currently ranks #47019 daily, #46985 weekly, #47443 monthly by momentum on Trending Repos; its best-ever rank is #1317.