[StableDiffusion] Visual prompt builder for AI images/videos

Over the last 4 years spend hours after hours experimenting with prompts for AI image and video models as well as AI coding. One thing started to annoy me though. Most prompts end up turning into a huge messy wall of text. Stuff like: `“A cinematic shot of a man walking in Tokyo at night, shot on ARRI Alexa, 35mm lens, f1.4 aperture, ultra-realistic lighting, shallow depth of field…”` And I end up repeating the same parameters over and over: * camera models * lens types * focal length * lighting setups * visual styles * camera motion After doing this hundreds of times I realized something. Most prompts actually follow the same structure again and again: subject → camera → lighting → style → constraints But typing all of that every single time gets annoying. So I built a visual prompt builder that lets you compose prompts using controls instead of writing everything manually. You can choose things like: • camera models https://preview.redd.it/550hvv4cn3pg1.png?width=1380&format=png&auto=webp&s=88cb57be8d0d9e03b590de9a24fc64a20d625380 • camera angles https://preview.redd.it/vst9lw44n3pg1.png?width=1232&format=png&auto=webp&s=e68d803297277760a9a097a5329989033b844369 • focal length • aperture / depth of field • camera motion https://preview.redd.it/e5snxt5an3pg1.png?width=1236&format=png&auto=webp&s=f10ce46fb87fc836f3b4612fbbd399b771b92b16 • visual styles https://preview.redd.it/gvcxony1n3pg1.png?width=1226&format=png&auto=webp&s=abf3963e547bc55aaae15ef046a83d9e715e9bf2 • lighting setups The tool then generates a structured prompt automatically. So I can also save my own styles and camera setups and reuse them later. It’s basically a visual way to build prompts for AI images and videos, instead of typing long prompt strings every time. If anyone here experiments a lot with prompts I’d genuinely love honest feedback: [https://vosu.ai/PromptGPT](https://vosu.ai/PromptGPT) Thank you <3