Hello,
I'm an AI engineer passionate about deep learning and the latest research in the field. I specialize in image generation, particularly Diffusion Models, which are the current state of the art for this task. My background is more theoretical, since I studied Mathematics and Applied Statistics, but I'm also a practitioner with experience in building and training models using PyTorch or higher level libraries such as HuggingFace Diffusers and building complex workflows in open-source tools like ComfyUI.Posts
- Bad Apple but it's GPT-2 XL Attention MapsFeb 15 2026Optimizing learnable embeddings so a frozen GPT-2 XL model displays video frames in its attention maps.
- Understanding ComfyUI's Beta Noise ScheduleNov 10 2025How beta distribution sampling improves diffusion model quality with fewer steps and how to use split-sampling in ComfyUI.