DreamX-Creator: Native 2K Audio-Video Generation via 7B Model

GD-ML · hf · 2026-09-01

DreamX-Creator is a compact 7B native joint audio-video generator. It employs cross-modal attention, progressive joint training, reinforcement learning with multimodal feedback, and an autoregressive 2K refinement pipeline to produce synchronized high-resolution outputs.

Original post →

More from Multimodal

Multimodal channel →