SHI-Labs/Matting-Anything
Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.
PythonMIT
Issues
- 2
Inference on own image trimap pair
#21 opened by heorhiikalaichev - 0
HuggingFace demo down
#22 opened by guanyanchu - 6
- 6
- 3
pip install --upgrade diffusers[torch]
#7 opened by chrisbward - 0
Inference on custom dataset
#20 opened by brianneoberson - 1
Request for adding object function
#19 opened by ZC0102-shu - 1
- 1
Connection error when running gradio_app.py
#16 opened by ZC0102-shu - 2
Request for the Distinctions646 dataset
#15 opened by maoyj1998 - 3
- 1
Suggestion - Integrate MobileSAM into the pipeline for lightweight and faster inference
#14 opened by mdimtiazh - 1
- 1
HuggingFace demo seems down
#12 opened by ogencoglu - 2
training code release
#11 opened by maoyj1998 - 3
Question regarding smoothing of edges
#9 opened by ghpkishore - 2
How long it takes to train MAM?
#5 opened by KainingYing - 1
Please list CUDA version as 11.7 in docs
#8 opened by chrisbward - 1
- 3
For Video?
#3 opened by p0mad - 5