DreaMoving

Preview：

Introduce：

DreaMoving is a controllable video generation framework based on diffusion model for generating high quality custom human dance videos. Given the target identity and pose sequence, DreaMoving can generate a video of the target identity that drives the pose sequence to dance anywhere. To this end, we propose a video control network for motion control and a content seeker to retain identity information. The model is easy to use and can be adapted to most stylized diffusion models to produce diverse results.

Stakeholders:
Users can use DreaMoving to generate high-quality customized human dance videos by simply providing the target identity and pose sequences.
Usage Scenario Examples:

• Use DreaMoving to generate a video of a girl dancing on the beach
• Use DreaMoving to generate a video of a man dancing in front of an Egyptian pyramid
• Use DreaMoving to generate a video of a girl dancing in a French town

The features of the tool:

• Video generation based on diffusion model
• Supports custom poses and identities
• Provides motion control and content seeker
• Supports simple text and image descriptions

Tool’s Tabs: Video generation,Ai image to video