Merging artistic insight with deep technical knowledge to push creative boundaries in real-time rendering and AI-driven content generation.
As a seasoned Technical Artist with over 10 years of expertise in real-time rendering and digital content creation, I specialize in the practical application and integration of Generative AI within real-time pipelines, virtual production, and product visualization.
My expertise includes developing custom Gen AI tools, optimizing complex workflows, and pioneering innovative solutions using technologies like Unreal Engine and advanced AI-driven content generation techniques. I effectively merge artistic insight with deep technical knowledge to push creative boundaries.
UE5, Real-time Visualization, Blueprints, Shaders, Materials, Lighting, Virtual Production
ComfyUI, Stable Diffusion, LoRA Training, OpenAI API, Eleven Labs, Whisper, Custom LLMs
Houdini, Cinema 4D, ZBrush, Blender, Marmoset, Substance Painter/Designer, SpeedTree
Python, C++ (Unreal), Git, Perforce, Pipeline Development, Workflow Automation
A custom ComfyUI node that generates detailed Stable Diffusion prompts using Qwen3-8B running locally via Ollama. Features 7 style presets (Cinematic, Anime, Photorealistic, Fantasy, Abstract, Cyberpunk, Sci-Fi), mood and atmosphere controls, and adjustable creativity parameters — all integrated directly into ComfyUI workflows.
View on GitHub
QLoRA fine-tuning pipeline for training Qwen3-4B to generate cinematic video diffusion prompts. Specializes in the De Forum Art Film aesthetic — noir-influenced, atmospheric, psychologically minimal. Features eval split with early stopping, WandB monitoring, and full export to GGUF/Ollama for local deployment.
View on GitHub
A comprehensive Python toolkit for local deployment of Microsoft's Florence-2 vision model. Process images with state-of-the-art computer vision capabilities including object detection, image captioning, and visual analysis.
View on GitHub
A powerful custom node for ComfyUI that efficiently removes backgrounds and handles transparency, streamlining complex image composition workflows.
View on GitHub
A custom Python-based node that provides accurate depth estimation from 2D images. Essential for 3D reconstruction, depth-aware masking, and post-processing effects in generative workflows.
View on GitHub
A utility node for ComfyUI that provides advanced control over seed generation, ensuring reproducibility and enabling precise iteration in generative art workflows.
View on GitHub
An advanced face detection node for ComfyUI, leveraging state-of-the-art models to accurately identify and process faces within complex scenes for targeted editing and enhancement.
View on GitHubI'm currently open to new opportunities and collaborations. Feel free to reach out via email or connect with me on social media.
gero@limbicnation.com