Vidu Q2: Reference to Video
Generate videos with reference-based consistency for up to 3 subjects, maintaining character and style continuity across the video sequence with cinematic camera movements.
About
The 'Vidu Q2: Reference to Video' workflow is designed to generate videos that maintain character and style consistency across sequences, making it ideal for projects requiring cohesive visual storytelling. This workflow leverages the Vidu Q2 and Vidu models, which are specifically tuned for handling multiple subjects while preserving their distinct features and styles throughout the video.
What you provide
- Reading the workflow
Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.
Try in CloudQuestions & answers
Currently, the workflow supports up to three subjects to maintain optimal consistency and performance.
The LoadImage node supports common image formats such as JPEG, PNG, and BMP.
Ensure that your reference images are high-resolution and well-lit to provide the models with clear details for processing.
Yes, the Vidu2ReferenceVideoNode allows for configuration of cinematic camera movements to enhance the video’s visual appeal.