FrameThrower

FrameThrower is a searchable library of film stills designed to speed up reference gathering and prep. You can search frames by visual qualities like lighting, composition, colour and shot size, then collect examples into lookbooks for pitching or production.

The tool indexes frames with searchable tags such as lighting, lens character, shot size, colour grade, time of day and people in the shot, so you can describe what you want and get matching images. Saved references can be exported as PDF boards or ZIP files.

Developers and technical creatives get access to a REST API, an MCP server for Claude and ChatGPT, an npm SDK and a ComfyUI node to pull cinematography references into other workflows. FrameThrower was created by senior filmmakers and advertising creatives. https://framethrower.ai/

• AI-powered visual search for film stills
• Tags for lighting, lens, shot size, colour grade, time of day and cast
• Save to lookbooks and export PDF boards or ZIPs
• REST API, MCP server, npm SDK and ComfyUI node for integrations