Search

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

A Music Semantic VAE for music understanding, generation, and high-fidelity reconstruction.

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.

Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which increase speed by up to 1.7x