[New Project] Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

[tin2tin]

Is your feature request related to a problem? Please describe.
With Runway and Midjourney, just now releasing updates tackling visual reference input, to be able to do character, location, and style consistency in narrative images and video, maybe this project could very well be the open-source answer to this challenge?
https://github.com/Phantom-video/Phantom

[nitinmukesh]

If you want to try this model and don't know already.
https://github.com/deepbeepmeep/Wan2GP/

Supports most of Wan based models. I started using it very recently and it's quite good.

[tin2tin]

Phantom_wan 14b released: https://huggingface.co/bytedance-research/Phantom/tree/main