Upload folder using huggingface_hub

README.md

@@ -30,7 +30,7 @@
 ## 📖 Introduction
 
 This is the official implementation for the paper: [HPSv3: Towards Wide-Spectrum Human Preference Score]().
-First, we introduce a VLM-based preference model **HPSv3**, trained on a "wide spectrum" preference dataset **HPDv3** with 1.08M text-image pairs and 1.17M annotated pairwise comparisons, covering both state-of-the-art and earlier generative models, as well as high- and low-quality real-world images. Second, we propose a novel reasoning approach for iterative image refinement, **COHP**, which efficiently improves image quality without requiring additional training data.
+First, we introduce a VLM-based preference model **HPSv3**, trained on a "wide spectrum" preference dataset **HPDv3** with 1.08M text-image pairs and 1.17M annotated pairwise comparisons, covering both state-of-the-art and earlier generative models, as well as high- and low-quality real-world images. Second, we propose a novel reasoning approach for iterative image refinement, **CoHP(Chain-of-Human-Preference)**, which efficiently improves image quality without requiring additional training data.
 
 <p align="center">
   <img src="assets/teaser.png" alt="Teaser" width="900"/>
@@ -46,7 +46,7 @@ First, we introduce a VLM-based preference model **HPSv3**, trained on a "wide s
 2. [🌐 Gradio Demo](#🌐-gradio-demo)
 3. [🏋️ Training](#🏋️-training)
 4. [📊 Benchmark](#📊-benchmark)
-5. [🎯 COHP (Consistency-guided Human Preference Optimization)](#🎯-cohp-consistency-guided-human-preference-optimization)
+5. [🎯 CoHP (Chain-of-Human-Preference)](#🎯-cohp-chain-of-human-preference)
 
 ---
 
@@ -146,9 +146,12 @@ Human Preference Dataset v3 (HPD v3) comprises 1.08M text-image pairs and 1.17M
 </details>
 
 #### Download HPDv3
-```bash
-huggingface-cli download --repo-type dataset MizzenAI/HPDv3 --local-dir /your-local-dataset-path
 ```
+HPDv3 is comming soon! Stay tuned!
+```
+<!-- ```bash
+huggingface-cli download --repo-type dataset MizzenAI/HPDv3 --local-dir /your-local-dataset-path
+``` -->
 
 #### Pairwise Training Data Format
 
@@ -242,7 +245,7 @@ To evaluate **HPSv3 preference accuracy** or **human preference score of image g
 
 ---
 
-## 🎯 COHP (Consistency-guided Human Preference Optimization)
+## 🎯 CoHP (Chain-of-Human-Preference)
 
 COHP is our novel reasoning approach for iterative image refinement that efficiently improves image quality without requiring additional training data. It works by generating images with multiple diffusion models, selecting the best one using reward models, and then iteratively refining it through image-to-image generation.