Alibaba's 7B DreamX-Creator jointly generates synced audio-video with 1-step 2K refinement

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Jiashu Zhu, Yanhao Zheng, Ruitian Tian, Rujing Dang, Shen Zhang, Bingze Song, Jiachen Lei, Ruimin Lin, Jiahong Wu, Xiangxiang Chu

cs.CV, cs.SD

2026-09-01

7B joint audio-video generator with gated cross-modal attention and a 1-step 2K refiner. Beats most open baselines on DeSync; trails larger systems on audio aesthetics.

What problem this solves

Most video generators either skip audio or add it after the fact. Speech, impacts, ambience and camera motion are jointly determined; a cascade cannot model that reciprocity. Native joint systems exist, but almost none combine downloadable weights, a local 2K path, and a backbone under 10B. LTX-2.3 is 22B, MOVA is 32B/18B, MAGI-2 Preview is 114B/6B. DreamX-Creator 1.0 ships a 7B joint generator plus a local 2K refiner.

Method

The generator takes a first frame and a text prompt, then jointly denoises audio and video latents with flow matching. The first half of the network keeps the two streams independent. The latter half opens paired audio-to-video and video-to-audio cross-attention. Token rates differ, so positions are mapped onto a shared timeline and temporal RoPE is applied to cross-modal queries and keys; neither stream is resampled.

Each cross-attention head is scaled by a sigmoid gate that depends on both the target hidden state and the attention output. A direction mask picks A2V, V2A or Joint per sample; the gate only scales an already-active path. In directional modes the target stream is noisier than the conditioner, and stop-gradient is applied to the conditioner keys and values so the target loss cannot rewrite the other backbone.

Clips are cut at scene boundaries and filtered with Q-Align, Audiobox Aesthetics, Synchformer and SyncNet, then captioned jointly by Qwen3-Omni. Speech is 45.0% of the data, event sounds 33.4%. Training runs in three stages: LoRA warmup on the latter half, full-parameter pretraining, then high-quality finetuning. Reinforcement learning routes video, audio and cross-modal advantages to the matching streams. The 2K refiner starts as a bidirectional multi-step teacher, becomes an autoregressive multi-step model, and is distilled with DMD into a student that does one denoising evaluation per temporal chunk. Audio is left untouched in this stage.

Results

On Verse-Bench the 7B model is competitive with open research baselines and mixed against larger open-weight systems.

MethodParamsVQ↑LSE-C↑DeSync↓
NAVA6.3B0.61167.72610.2342
Ovi10B0.65427.30950.4730
Ours7B0.65687.80180.1902
Ours (RL)7B0.65737.83610.1351
Ours (Refiner)7B0.69307.69790.1731
LTX-2.322B0.62857.67680.2412
MiniMax-H333B0.64298.73540.2708

RL cuts DeSync from 0.1902 to 0.1351. The refiner lifts VQ to 0.6930 and slightly hurts sync. In a blind study, video-quality win rates against Ovi, UniAVGen, NAVA and DaVinci sit between 61.7% and 73.7%. Against Wan2.7, Kling v3 and MiniMax-H3, audio quality and AV alignment both lose more than they win.

Why it matters

This is the smallest disclosed open-weight native joint audio-video backbone with a local 2K path. Anyone working on joint modeling, sync rewards or video super-resolution distillation can start from a 7B checkpoint instead of a hosted API. It does not beat 22B/33B systems on audio aesthetics or cross-modal semantics. Treat it as a reproducible research base, not a leaderboard winner.

Limitations

The 7B model trails LTX-2.3 and MiniMax-H3 on Content Enjoyment, Content Usefulness, Production Quality and ImageBind, and trails MiniMax-H3 on lip sync (8.7354). The human study under-samples highly dynamic, compositionally complex scenes. Refinement raises DeSync from 0.1351 to 0.1731, so resolution and sync do not improve together. RL is trained on only 1,000 first-frame/prompt pairs. The conclusion still describes RL and 2K refinement as designs with validation requirements, which sits awkwardly next to the reported tables; trust the tables.

Terms

Source

Related papers

All paper explainers