Vidu Q2 Reference-Guided Images
Vidu Q2 generates detailed images from prompts and can build new ones from a reference image, preserving the core identity while changing everything else.
- Vidu
- 2 variants
- From $0.10 per run
- Price
- See price
- Speed
- See speed
- Best for
- Text to Image
- Price
- See price
- Speed
- See speed
- Best for
- Image edit · Image to Image
More from Vidu.
A family groups the versions of one model line. Open one to compare its variants side by side.
Working with Vidu Q2.
Vidu Q2 is the image side of Vidu. Text-to-Image produces visually rich results with style control, while Reference-to-Image combines a reference image with a prompt and keeps the core identity of the subject intact through the regeneration.
When to choose Vidu Q2
Choose Vidu Q2 when you want identity-preserving image generation from a single reference. The other Vidu families are video-only, so this is the one for stills.
Choosing between the variants
Text to Image starts from a prompt with style and detail control. Reference to Image is the identity-preserving route and is what you want when a specific subject must survive into the new picture.
Questions about Vidu Q2
The short answers. For anything specific to your setup, talk to our team.
Talk to an engineerPlan for your expected volume.The core identity of the subject in your reference, while the prompt drives style, setting and composition around it.
No. Q2 produces still images; Vidu Q1 and Vidu 2.0 are the video families.
The text variant exposes style control and creative flexibility alongside prompt detail, so output can be steered without a reference image.