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.
Python Updated 23 days ago 1 commits 55 stars
echo-ai|Mirror: LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler (⭐55)
23 days agoE2B SandboxFirecracker microVMpython
No executable code files found in this repository.
About
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.
Readme
55 stars
2 forks