Dmitry K.

I work with generative AI models to create visual content: video, images, 3D and immersive VR/AR environments. I also automate the work around it with AI agents and workflows. Most of it runs locally in ComfyUI (Flux, Wan, custom LoRAs). I orchestrate it with n8n, so batches are routed, checked and retried on their own and run unattended overnight. Lately that's vertical drama and character driven video: consistent characters, matched voices, cinematic shots. I have 8+ years in XR and 3D, so I know how the whole system fits together: device, backend and user. I've built iOS capture apps, multi user VR on Photon Fusion, AWS backends with WebSocket connections, and a voice assistant wired into a live app. That's why I can take a project from idea to a working result, not just deliver one piece of it. I take on: - AI video and short series - Workflow automation with n8n and LLM agents - Image generation, custom ComfyUI workflows and LoRA training - 3D scans and Gaussian Splatting - VR/AR and Unity projects Send me a message about your project. I can give you a quick consultation or help build it, and I'm open to different ways of working together.