Hugging Face's logo

Spaces:
BoltzmannEntropy
/
vlms
Running

App Files Community
BoltzmannEntropy commited on
Commit
b100632
•
1 Parent(s): 01a4f8e

readme

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ Welcome to the Hugging Face Space (https://huggingface.co/spaces/BoltzmannEntrop
15
 
16
  <h1 align="center">
17
  <img src="static/image.jpg" width="50%"></a>
18
- <h6> (Source wang2023allseeing: https://huggingface.co/datasets/OpenGVLab/CRPE?row=1) <h6>
19
  </h1>
20
 
21
  This repository contains the core code for a multi-model framework that enhances image interpretation through the combined power of several Vision-and-Language Modeling (VLM) systems. VLM-Image-Analysis delivers detailed, multi-faceted analyses of images by leveraging N cutting-edge VLM models, pre-trained on a wide range of datasets to detect diverse visual cues and linguistic patterns.
 
15
 
16
  <h1 align="center">
17
  <img src="static/image.jpg" width="50%"></a>
18
+ <h6> (Source: wang2023allseeing: https://huggingface.co/datasets/OpenGVLab/CRPE?row=1) <h6>
19
  </h1>
20
 
21
  This repository contains the core code for a multi-model framework that enhances image interpretation through the combined power of several Vision-and-Language Modeling (VLM) systems. VLM-Image-Analysis delivers detailed, multi-faceted analyses of images by leveraging N cutting-edge VLM models, pre-trained on a wide range of datasets to detect diverse visual cues and linguistic patterns.