SahilCarterr/Wan2.2
Wan: Open and Advanced Large-Scale Video Generative Models
Wan: Open and Advanced Large-Scale Video Generative Models
This project fine-tunes YOLOv8 to detect fashion items, segments them using SAM (Segment Anything Model), and applies ControlNet inpainting to enhance their style and appearance based on creative prompts.
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Calligrapher: Freestyle Text Image Customization
This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord
This repository designed to extend the capabilities of the Hugging Face Diffusers library by adding advanced and custom functionalities to its pipelines.
This project uses video analysis and location detection to identify road issues captured via dash cams. Detected problems are analyzed and automatically marked on maps with their precise locations, providing real-time alerts and improving road safety.
Fine-tune popular transformer models like DistilBERT, BERT Base, BART Large MNLI, LLaMA 3 (8B), Mistral 7B, and Gemma 7B for various NLP tasks. This repository provides streamlined scripts and configurations for efficient model adaptation and evaluation.
This repository contains the Perturbed Attention Guidance (PAG) Img2Img Pipeline for Stable Diffusion, now integrated into the diffusers library by me.
This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
Personal blog with Jupyter notebooks
Inpaint images with ControlNet
Comfy-ui samples
Convolution-Neural-Network-Basic-Models
A simple port scanner using python
U-NET PyTorch Modals
Data Scientist Job Salary Visualization And ML