DreamX-Creator: Open Joint Audio-Video Generation at 2K

ComfyUI Wiki

DreamX-Creator 1.0 is AMap's open 7B model that generates synchronised video and audio together, with a 1-step 2K refiner and native ComfyUI nodes.

D

DreamX-Creator

Video GenerationJoint Audio-Video2KComfyUI

DreamX-Creator 1.0 is an open research framework from the AMap ML team for native joint audio-video generation. A 7B generator models video and audio streams together through gated cross-modal attention, and an autoregressive 1-step refiner super-resolves the result to 2K. Native ComfyUI nodes are available.

Models

ModelTypeDescriptionLicenseReleased
DreamX-Creator 1.0Video + Audio7B joint audio-video generator with a causal 1-step 2K refinerApache-2.02026-09

Select a model above for curated weight downloads, tutorials, and related information.

Comments

Sign in with GitHub to join the discussion.

Loading comments…