Jit Roy

Native ComfyUI custom node for WeeLLM: Run multi-billion parameter diffusion models (FLUX, SD3, MiniMax) under 4GB VRAM using layer-streaming inference. Official Repo Link: https://github.com/Jit-Roy/WeeLLM

MyBro is an AI mental health companion that engages in friendly conversations, monitors emotional well-being, and offers guidance through a secure and user-friendly llm.

Turn long videos into viral clips automatically. Long-form is a drag, but clipping shouldn't be. ✂️ Just drop an instruction like "Extract the funniest moments" or "Only clip Speaker B," and our LLM does the rest. It’s giving unmatched control.

An AI-powered interactive fiction and storytelling engine that brings characters to life through dynamic conversations and objective-driven gameplay.

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.