DUTO is an AI image and video workflow builder. You design reusable visual workflows on a canvas that combine models, prompts, references, batch generation, and creative automation, so the process behind an AI output can be saved, inspected, and reused instead of recreated as a one-off generation.

DUTO is built for creators, marketers, and teams who need repeatable AI image and video output. It fits product video, ad creative, UGC, storyboard, and ecommerce workflows, and any team that needs the process behind a generation to survive beyond a single result.

You start from a prompt or a template and assemble a workflow on a visual canvas. Each step can set its own model, prompt, references, and batch options, then connects to the next step. Running the workflow produces consistent image and video output every time, and you can reuse or adjust the same workflow for new inputs.

DUTO is free to start and currently in public beta. Building and running visual workflows is free, and credit-based generation is available for heavier image and video models. A budget mode is offered for lower-cost runs.

DUTO connects leading image and video models in a single flow, including options such as Veo 3, Kling, Sora, Seedream, and Seedance. You can combine different models across the steps of one workflow rather than being locked into a single provider.

A workflow is a reusable canvas of image and video generation steps you build and run directly. A storyboard is an AI-assisted way to plan a multi-shot video before generating it. Both produce visual output, and storyboard planning is available alongside the core workflow builder.