In today’s world, data is everything. When we upload images, videos, or text to commercial AI apps, we rarely know what happens behind the scenes, and legal protection for sensitive personal information is limited. This workshop used open source tools like ComfyUI running locally on consumer grade computers, giving participants control over their creative process, results, and data. The goal was not only to generate content, but to understand how to negotiate with AI, using workflows that gave us agency, transparency, and freedom.

 

Designed for beginners, the workshop focused on producing precise images, videos, and 3D models from existing site or project images. Participants learned core concepts such as latent space, VAEs, checkpoints, and prompt structures, then worked through image, video, and 3D workflows using ControlNet, Flux, WAN 2.2, Gemini 2.5 Flash Image, and Hunyuan 3D or Sparc 3D, with final refinement in Rhino3D.

 

By the end, participants completed the full pipeline from text to image, image to video, and image to 3D model, resulting in a human - AI negotiated output with the help of AI’s latent capabilities.