Text to video
Choose the supported inputs and model-aware controls in one focused AllVideoAI workflow.
Alibaba · Video model
Create with Wan 2.6Wan 2.6
A versatile Wan generation model for prompt-driven scenes and animated source images.
Model overview
Meet Wan 2.6
Wan 2.6 combines text, image, and reference-driven video generation with synchronized audio. Its text workflow supports single or multi-shot structure and can expand a simple prompt into a more detailed internal script.
The family is useful for ads, explainers, trailers, and short social stories that need coherent characters, stable scene semantics, landscape or vertical delivery, and several duration or quality choices.
Image to video
Choose the supported inputs and model-aware controls in one focused AllVideoAI workflow.
Prompt control
Choose the supported inputs and model-aware controls in one focused AllVideoAI workflow.
Prompting tip
For multi-shot work, label each shot and keep the same character description across the sequence. Use prompt expansion when the idea needs more coverage.
AllVideoAI Studio
Compare models and create in one workspace
Supported creation modes and parameters adapt to the selected model, with credit pricing confirmed before generation.