Model Hub

Text-to-video diffusion, 1.3B parameters, 480x832 clips.

Text-to-video diffusion transformer, 2B parameters, 720x480 clips with classifier-free guidance.

Dual-expert image-to-video diffusion, two 14B denoisers with boundary switching, 480P and 720P clips.

Image-to-video diffusion, 14B parameters, 480P clips.

Open text-to-video generation, MMDiT architecture, 11B parameters.

Text-to-video generation at native 720x1280, 88-frame clips, 3D-RoPE diffusion transformer with T5 conditioning.

Image-to-video generation at native 720x1280, 88-frame clips conditioned on a first frame.

High-motion text-to-video generation, asymmetric diffusion transformer, 10B parameters.

All-in-one video creation and editing (VACE), 1.3B parameters. Text-to-video generation is validated and reproducible: at 480x832, 9 frames, guidance 5.0 it renders bit-identically to its 2026-06-28 validation on both engines (re-checked 2026-09-03). Declared limitation at this release: generation conditioned on a REFERENCE IMAGE is not supported - that path stops on a channel-size mismatch and is tracked as a named fix. Use the prompt-only mode; the sibling Wan2.1-T2V-1.3B covers plain text-to-video as well.

Efficient 720p text-to-video generation, 2B parameters, linear-attention diffusion transformer.