Using Comfy to Go Beyond the Models: Custom Workflows for Commercial and Film Production
Join us for a conversation with Ezra Paulekas (Creative Director) and Ariel Klevecz (Tech Lead/Content Automation) from Tool, on using ComfyUI as a flexible production tool rather than a single model or plugin. Instead of centering on any one model, Ezra and Ariel will walk through how Tool builds custom Comfy workflows around what a specific project actually needs, and how those workflows get integrated into traditional filmmaking, VFX, and post-production pipelines. The throughline across every project: going beyond what a model can do out of the box, and using Comfy to build the exact tool the production requires. Projects we'll break down: 🎬 AMD | CES 2026 Opening Film — Custom Wan 2.1 workflows for precise first-person hand movement and extreme outpainting on a 5K, 32:9 keynote film. https://toolofna.com/ai/work/amd-ces2... 🌸 Flower (Ariel's personal project) — A song's loudness shapes a mask Wan 2.1 paints inside, chained frame by frame to grow flowers for the length of the track. https://wan-audio.raptor.pizza/ 🍬 Starburst | Different Every Time — A commercial campaign generating a different animated world with every Starburst eaten — Ezra's first project using ComfyUI in production. https://toolofna.com/ai/work/starburs... 🎞️ Everywhere/Nowhere (Ezra's personal project) — An experimental short blending live action with early ComfyUI video-to-video: compositing layers, stop-motion, and a generative title sequence, moving between Comfy, After Effects, and Flame. What we'll cover: 🛠️ Building custom Comfy workflows around what a production actually needs, not what a model does by default 🛠️ Precise first-person hand/performance control and extreme-resolution outpainting with Wan 2.1 (AMD CES film) 🛠️ Audio-reactive generation and letting a song's loudness constrain what Wan paints, frame-chained (Flower) 🛠️ Comfy in a commercial pipeline generating a different world per execution (Starburst) 🛠️ Comfy-generated compositing layers, stop-motion, and title sequences moving between Comfy, After Effects, and Flame (Everywhere/Nowhere) Drop your questions and prompt ideas in chat and we'll try to run them live. ⏰ Subscribe and enable notifications to catch the stream live 💬 Submit your questions in chat during the broadcast or before the stream in the comments! 👍 Leave a like if you'd like to see more AI video model comparisons!