aliasgharkhani/SLiMe
1-shot image segmentation using Stable Diffusion
This tool helps researchers and computer vision practitioners automatically outline specific parts of objects within images, even with very few examples. You provide an image and a corresponding hand-drawn mask highlighting the object or part you want to identify. The tool then generates a model that can identify and segment that same object or part in other, unseen images. It is ideal for those working on tasks like medical image analysis, object recognition, or automated visual inspection.
143 stars. No commits in the last 6 months.
Use this if you need to quickly segment specific, novel objects or parts in images with minimal training data.
Not ideal if you need a fully automated, zero-shot segmentation solution without any initial examples, or if you prefer a graphical user interface over command-line tools.
Stars
143
Forks
19
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aliasgharkhani/SLiMe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration