Hugging Face's logo

TheDenk
/
Qwen2.5-VL-3B-TrackAnyObject-LoRa-v1

Image-Text-to-Text
Transformers
Safetensors
English
multimodal
tracking
lora
Model card Files
xet
Community
1
New discussion

Fine-tuning VLM vs. combining with SAM2 for object tracking, which path should I choose? Looking for experience sharing

1
#1 opened 26 days ago by
weihongliang