Lists (1)
Stars
[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
๐งข๐ถ๏ธ๐ฅผ๐๐๐งณ A curated list of cool resources about GenAI-Fashion, including ๐papers, ๐workshops, ๐companies & products, ...
๐ A collection of sketch based application papers.
Safely manage multiple Kubernetes clusters by defining safe contexts and protected commands.
๐ Cross attention map tools for huggingface/diffusers
Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.
AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency.
Select, put and delete data from JSON, TOML, YAML, XML and CSV files with a single tool. Supports conversion between formats and can be used as a Go package.
Open source Structure-from-Motion pipeline
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
๐ฆ Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use thโฆ
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Codebase for performing various experiments with Stable Diffusion, supported by the diffusers library.
Extension for ComfyUI to evaluate the similarity between two faces
custom node for ComfyUI to perform simple math operations
Linux virtual machines, with a focus on running containers
An extensive node suite for ComfyUI with over 210 new nodes
Automation for Kubernetes development and testing. Spin up production-like environments for development, testing, and CI on demand. Use the same configuration and workflows at every step of the proโฆ
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
An engine for displaying slips, the next-gen version of slides