yeungchenwa/OCR-SAM
Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting
Python
Issues
- 0
- 0
maximum resolution of 1024x1024
#46 opened by himberjack - 0
Case sensitive?
#45 opened by qiqigit - 1
SAM for Text部分问题请教
#44 opened by Dchenlittle - 1
数据集问题
#43 opened by Dchenlittle - 1
how about combine it LLM like vary does?
#42 opened by lucasjinreal - 2
Difference in performance between mmocr_sam_erase.py and mmocr_sam_erase_app.py
#41 opened by haaaaak - 1
when using Inpainting demo there is an error
#40 opened by Sleepybear66 - 3
video pipeline
#32 opened by darkzbaron - 0
请叫部署的问题
#39 opened by yang-chenyu104 - 0
Is there any way to port this project to the existing StableDiffusion?
#38 opened by writingdeveloper - 1
why the picture is blurry after erasing
#37 opened by winderzhang - 2
- 1
Suggestion - Integrate MobileSAM into the pipeline for lightweight and faster inference
#31 opened by mdimtiazh - 3
About the example images
#34 opened by Chen-Li-17 - 2
About the mmocr_inferencer error
#33 opened by Chen-Li-17 - 1
- 2
Amazing, thanks for sharing!
#23 opened by wendlerc - 1
The effect is not very good
#29 opened by Henryplay - 1
Argument parsing issue in `mmocr_sam_erase.py`
#27 opened by wangruohui - 1
Is this the intented behavior?
#26 opened by wendlerc - 1
errors when loading model
#16 opened by tensorboy - 3
- 2
ldm ckpt not available
#21 opened by mattgithub1919 - 2