Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.

Join our Discord to generate videos of the Zoom Call LoRA for free.

Wan2.1 14B T2V v1.0:

This was trained on the Wan.21 14B T2V model.

The trigger word is: '[z00m_ca11]'. You can alternatively just call it a zoom call or even just describe the zoom call in detail by referring to locations of participants of the call, as well as the descriptions of the participants themselves.

See below for some prompt examples that worked well for me. You can also check the videos I've posted here for the captions that were used to generate them.

Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 6.0

Flow shift = 5.0

Check out all our LoRAs on our page: https://app.remade.ai/

Prompt Examples:

The video shows a Zoom call with three participants. The top left box shows a pirate captain in full uniform, surrounded by treasure chests. The top right box shows a medieval knight seated on a horse inside an office. The bottom box shows a person wearing a superhero cape, calmly presenting charts while hovering mid-air.

The video shows a [z00m_ca11] with four participants. The top left box shows a person in a dress shirt and blazer, sitting at a desk with a lamp behind them. To their right, a person with a headset is in a modern office space. The bottom left shows a person wearing a suit and tie, seated with a blurred background. The bottom right shows a person in formal clothing with their camera on and microphone muted.

The video shows a [z00m_ca11] with four participants. In the top left box, Mario is enthusiastically gesturing. To his right, Bugs Bunny is munching on a carrot. The bottom left box shows Darth Vader breathing ominously. The bottom right box features Snoopy typing on a typewriter.​

Let me know if there are any questions, I'll be happy to help!