What Claude can make on its own
Anthropic's help center says Claude doesn't generate photos or illustrations the way image tools do, and builds diagrams, charts and interactive visuals with HTML and SVG instead. A video clip rendered by a video model is a different thing, and that is what a connector adds.
Which video models Claude can use through MakeMidas
MakeMidas lists video models from Google (Veo and Gemini Omni), Kuaishou (Kling), ByteDance (Seedance), MiniMax (Hailuo), Alibaba (Wan and HappyHorse) and xAI (Grok Imagine). Name one in your request, or ask for the cheapest.
A clip takes one to several minutes. Claude starts it, checks back until it is ready and then shows it in the chat. Videos are priced per second by resolution and charged to your MakeMidas credits; the AI video cost calculator works one out before you ask.
Starting from a picture
Most video models can start from a first frame, and some move between a first and a last frame. Claude does not pass files you attach to connectors. To start from a picture, paste a public link to it, or ask Claude for a MakeMidas upload link, which opens MakeMidas in your browser to add the picture there. Claude can also make the picture first with an image model, then animate it.
In Claude Code
In Claude Code, run claude mcp add --transport http makemidas https://makemidas.com/api/mcp, then type /mcp to sign in. Claude Code can also run the MakeMidas CLI, which saves results as files in your project; the agent skills teach it the options.