Sync folder via upload_folder API

.gitattributes

@@ -61,3 +61,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 HPD/qwen/HPD_train_data_qwen.json filter=lfs diff=lfs merge=lfs -text
 HPD/qwen/HPD_train_data_qwen_rev.json filter=lfs diff=lfs merge=lfs -text
 HPD/train_data.json filter=lfs diff=lfs merge=lfs -text
+OpenAI-4o_t2i_human_preference/train_data.json filter=lfs diff=lfs merge=lfs -text

OpenAI-4o_t2i_human_preference/.gitattributes

@@ -0,0 +1,59 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mds filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+# Video files - compressed
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+*.webm filter=lfs diff=lfs merge=lfs -text

OpenAI-4o_t2i_human_preference/README.md

@@ -0,0 +1,356 @@
+---
+dataset_info:
+  features:
+  - name: prompt
+    dtype: string
+  - name: image1
+    dtype: image
+  - name: image2
+    dtype: image
+  - name: model1
+    dtype: string
+  - name: model2
+    dtype: string
+  - name: weighted_results_image1_preference
+    dtype: float32
+  - name: weighted_results_image2_preference
+    dtype: float32
+  - name: detailed_results_preference
+    dtype: string
+  - name: weighted_results_image1_coherence
+    dtype: float32
+  - name: weighted_results_image2_coherence
+    dtype: float32
+  - name: detailed_results_coherence
+    dtype: string
+  - name: weighted_results_image1_alignment
+    dtype: float32
+  - name: weighted_results_image2_alignment
+    dtype: float32
+  - name: detailed_results_alignment
+    dtype: string
+  splits:
+  - name: train
+    num_bytes: 10832696953.0
+    num_examples: 13000
+  download_size: 5203247080
+  dataset_size: 10832696953.0
+configs:
+- config_name: default
+  data_files:
+  - split: train
+    path: data/train-*
+license: cdla-permissive-2.0
+task_categories:
+- text-to-image
+- image-to-text
+- image-classification
+- reinforcement-learning
+language:
+- en
+tags:
+- Human
+- Preference
+- Coherence
+- Alignment
+- country
+- language
+- flux
+- midjourney
+- dalle3
+- stabeldiffusion
+- alignment
+- flux1.1
+- flux1
+- imagen3
+- aurora
+- lumina
+- recraft
+- recraft v2
+- ideogram
+- frames
+- OpenAI 4o
+- 4o
+- OpenAI
+size_categories:
+- 10K<n<100K
+pretty_name: OpenAI 4o vs. Ideogram V2 / Recraft V2 / Lumina-15-2-25 / Frames-23-1-25
+  / Aurora / imagen-3 / Flux-1.1-pro / Flux-1-pro / Dalle-3 / Midjourney-5.2 / Stabel-Diffusion-3
+  - Human Preference Dataset
+---
+
+<style>
+
+.vertical-container {
+    display: flex;  
+    flex-direction: column;
+    gap: 60px;  
+}
+  
+.horizontal-container {
+    display: flex;  
+    flex-direction: row;
+    justify-content: center;
+    gap: 60px;  
+}
+
+.image-container img {
+  max-height: 250px; /* Set the desired height */
+  margin:0;
+  object-fit: contain; /* Ensures the aspect ratio is maintained */
+  width: auto; /* Adjust width automatically based on height */
+  box-sizing: content-box;
+}
+
+.image-container img.big {
+  max-height: 350px; /* Set the desired height */
+}
+
+
+.image-container {
+  display: flex; /* Aligns images side by side */
+  justify-content: space-around; /* Space them evenly */
+  align-items: center; /* Align them vertically */
+  gap: .5rem
+}
+
+  .container {
+    width: 90%;
+    margin: 0 auto;
+  }
+
+  .text-center {
+    text-align: center;
+  }
+
+  .score-amount {
+margin: 0;
+margin-top: 10px;
+  }
+
+  .score-percentage {Score: 
+    font-size: 12px;
+    font-weight: semi-bold;
+  }
+  
+</style>
+
+# Rapidata OpenAI 4o Preference
+
+<a href="https://www.rapidata.ai">
+<img src="https://cdn-uploads.huggingface.co/production/uploads/66f5624c42b853e73e0738eb/jfxR79bOztqaC6_yNNnGU.jpeg" width="400" alt="Dataset visualization">
+</a>
+
+This T2I dataset contains over 200'000 human responses from over ~45,000 individual annotators, collected in less than half a day using the [Rapidata Python API](https://docs.rapidata.ai), accessible to anyone and ideal for large scale evaluation.
+Evaluating OpenAI 4o (version from 26.3.2025) across three categories: preference, coherence, and alignment.
+
+Explore our latest model rankings on our [website](https://www.rapidata.ai/benchmark).
+
+If you get value from this dataset and would like to see more in the future, please consider liking it ❤️
+
+## Overview
+
+The evaluation consists of 1v1 comparisons between OpenAI 4o (version from 26.3.2025) and 12 other models: Ideogram V2, Recraft V2, Lumina-15-2-25, Frames-23-1-25, Imagen-3, Flux-1.1-pro, Flux-1-pro, DALL-E 3, Midjourney-5.2, Stable Diffusion 3, Aurora, and Janus-7b.
+
+Below, you'll find key visualizations that highlight how these models compare in terms of prompt alignment and coherence, where OpenAI 4o (version from 26.3.2025) significantly outperforms the other models.
+
+<div style="width: 100%; display: flex; justify-content: center; align-items: center; gap: 20px;">
+    <div style="width: 90%; max-width: 1000px;">
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/fMf6_uredbYDY7Hzuyk9J.png" style="width: 95%; height: auto; display: block;">
+    </div>
+    <div style="width: 90%; max-width: 1000px;">
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/rMjvWjG8HFql65D47TGsZ.png" style="width: 100%; height: auto; display: block;">
+    </div>
+</div>
+
+## Master of Absurd Prompts
+The benchmark intentially includes a range of absurd or conflicting prompts that aim to target situations or scenes that are very unlikely to occur in the training data 
+such as *'A Chair on a cat'* or *'Car is bigger than the airplane.'*. Most other models struggle to adhere to these prompts consistently, but the 4o image generation model 
+appears to be significantly ahead of the competition in this regard.
+
+<div class="horizontal-container">
+  <div clas="container">
+   <div class="text-center">
+      <q>A chair on a cat.</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/kS2uE91Q3QAKxR205DxS_.webp" width=300>
+      </div>
+      <div>
+        <h3 class="score-amount">Imagen 3 </h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/KKQRsy9xzJVs7QsYyhuzp.jpeg" width=300>
+      </div>
+    </div>
+  </div>
+  <div clas="container">
+   <div class="text-center">
+      <q>Car is bigger than the airplane.</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/TWSsbPFxVJgaHW0gVCR2a.webp" width=300>
+      </div>
+      <div>
+        <h3 class="score-amount">Flux1.1-pro</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/7w3Ls8a6PmuR1ZR1J72Zk.jpeg" width=300>
+      </div>
+    </div>
+  </div>
+</div>
+
+That being said, some of the 'absurd' prompts are still not fully solved.
+
+<div class="horizontal-container">
+  <div clas="container">
+   <div class="text-center">
+      <q>A fish eating a pelican.</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/xsJ2E_0Kx5gJjIO6C29-Q.webp" width=300>
+      </div>
+      <div>
+        <h3 class="score-amount">Recraft V2</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/R7Zf5dmhvjUTgkBMEx9Ns.webp" width=300>
+      </div>
+    </div>
+  </div>
+  <div clas="container">
+   <div class="text-center">
+      <q>A horse riding an astronaut.</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/RretHzxWGlXsjD9gXmg2k.webp" width=300>
+      </div>
+      <div>
+        <h3 class="score-amount">Ideogram</h3>
+        <img class="big" src="https://cdn-uploads.huggingface.co/production/uploads/6710d82fd3a72fc574ea620f/qtVKN58c0JgCYKK2Xc5bT.png" width=300>
+      </div>
+    </div>
+  </div>
+</div>
+
+
+## Alignment
+
+The alignment score quantifies how well an video matches its prompt. Users were asked: "Which image matches the description better?".
+
+<div class="vertical-container">
+  <div class="container">
+   <div class="text-center">
+      <q>A baseball player in a blue and white uniform is next to a player in black and white .</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <div class="score-percentage">Score: 100%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/pzKcqdCXwVDZi5lwgoeGv.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Stable Diffusion 3 </h3>
+        <div class="score-percentage">Score: 0%</div>
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/rbxFhkeir8TUTK-vYDn6Q.jpeg" width=500>
+      </div>
+    </div>
+  </div>
+
+  <div class="container">
+   <div class="text-center">
+      <q>A couple of glasses are sitting on a table.</q>
+    </div>
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <div class="score-percentage">Score: 2.8%</div>
+        <img  src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/AY-I6WqgUF4Eh3thLkAqJ.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Dalle-3</h3>
+        <div class="score-percentage">Score: 97.2%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/3ygGq2P4dS6rfh5q-x3jb.jpeg" width=500>
+      </div>
+    </div>
+  </div>
+</div>
+
+## Coherence
+
+The coherence score measures whether the generated video is logically consistent and free from artifacts or visual glitches. Without seeing the original prompt, users were asked: "Which image has **more** glitches and is **more** likely to be AI generated?"
+
+<div class="vertical-container">
+  <div class="container">
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o </h3>
+        <div class="score-percentage">Glitch Rating: 0%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/DzuAiklD3R_pwe-yFtRM7.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Lumina-15-2-25 </h3>
+        <div class="score-percentage">Glitch Rating: 100%</div>
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/iAn4zphOEL_cpOorp0JNZ.jpeg" width=500>
+      </div>
+    </div>
+  </div>
+
+   <div class="container">
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o </h3>
+        <div class="score-percentage">Glitch Rating: 98.6%</div>
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/IeJHwzNc77tjVAKf8nGEk.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Recraft V2</h3>
+        <div class="score-percentage">Glitch Rating: 1.4%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/iCuVaPrVGbDeLHuqbMgkc.jpeg" width=500>
+      </div>
+    </div>
+  </div>   
+</div>
+
+## Preference
+
+The preference score reflects how visually appealing participants found each image, independent of the prompt. Users were asked: "Which image do you prefer?"
+
+<div class="vertical-container">
+  <div class="container">
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o</h3>
+        <div class="score-percentage">Score: 100%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/ve4DVzU0kZznjA9N0AdkO.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Lumina-15-2-25</h3>
+        <div class="score-percentage">Score: 0%</div>
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/zTZRillcEV85C9gfLa25L.jpeg" width=500>
+      </div>
+    </div>
+  </div>
+
+   <div class="container">
+    <div class="image-container">
+      <div>
+        <h3 class="score-amount">OpenAI 4o </h3>
+        <div class="score-percentage">Score: 0%</div>
+        <img  src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/0EmcYSDQeseS1XSWyG-lb.jpeg" width=500>
+      </div>
+      <div>
+        <h3 class="score-amount">Flux-1.1 Pro </h3>
+        <div class="score-percentage">Score: 100%</div>
+        <img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/664dcc6296d813a7e15e170e/MO7RnVUWC0gR84PIKDuyI.jpeg" width=500>
+      </div>
+    </div>
+  </div>
+</div>
+
+## About Rapidata
+
+Rapidata's technology makes collecting human feedback at scale faster and more accessible than ever before. Visit [rapidata.ai](https://www.rapidata.ai/) to learn more about how we're revolutionizing human feedback collection for AI development.

OpenAI-4o_t2i_human_preference/data.tar.gz.part-000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a08068ec2019d7c4dbdfdaa87100590be7052081b3aed1e94d70d2c14a211b
+size 5368709120

OpenAI-4o_t2i_human_preference/data.tar.gz.part-001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d8f50251f5d08b350e27bd7488a0cdfcc0830f3dcca1e4a83a3af473ec2963
+size 5196481255

OpenAI-4o_t2i_human_preference/read.py

@@ -0,0 +1,79 @@
+import pyarrow.parquet as pq
+from pathlib import Path
+import json
+from typing import List, Dict, Any, Optional
+
+def write_json(file_path: str, data: Any):
+    with open(file_path, "w", encoding="utf-8") as f:
+        json.dump(data, f, ensure_ascii=False, indent=4)
+        
+data_dir = Path("/inspire/qb-ilm/project/deepgen/wangdianyi-240107110022/BXH/RL_Data/OpenAI-4o_t2i_human_preference/data")
+out_dir = Path("/inspire/qb-ilm/project/deepgen/wangdianyi-240107110022/BXH/T2I-CoReBench-main/Bench/GEditBench-v2/Images")
+out_dir.mkdir(parents=True, exist_ok=True)
+
+parquet_files = sorted(data_dir.glob("*.parquet"))
+
+total_saved = 0
+total_skipped = 0
+
+save_data = []
+
+idx = 1
+save_data = []
+
+for parquet_path in parquet_files:
+    print(f"\nreading {parquet_path}")
+
+    pf = pq.ParquetFile(parquet_path)
+
+    for rg in range(pf.num_row_groups):
+        table = pf.read_row_group(rg).combine_chunks()
+        rows = table.to_pylist()
+
+        for i, row in enumerate(rows):
+            prompt = row['prompt']
+            image1_score = row['weighted_results_image1_preference']
+            image2_score = row['weighted_results_image2_preference']
+            gpt_value = ""
+            if image1_score > image2_score:
+                gpt_value = "Image 1 is better than Image 2."
+                image1_path = f'images/{idx}_chosen.png'
+                image2_path = f"images/{idx}_rejected.png"
+            elif image2_score > image1_score:
+                gpt_value = "Image 2 is better than Image 1."
+                image2_path = f'images/{idx}_chosen.png'
+                image1_path = f"images/{idx}_rejected.png"
+            
+            print(row['image1'].keys())
+            image1_byte = row['image1']['bytes']
+            import os
+            with open(os.path.join("/inspire/qb-ilm/project/deepgen/wangdianyi-240107110022/BXH/RL_Data/OpenAI-4o_t2i_human_preference",image1_path), "wb") as f:
+                f.write(image1_byte)
+            
+            
+            image2_byte = row['image2']['bytes']
+            with open(os.path.join("/inspire/qb-ilm/project/deepgen/wangdianyi-240107110022/BXH/RL_Data/OpenAI-4o_t2i_human_preference",image2_path), "wb") as f:
+                f.write(image2_byte)
+            
+            template = {
+                "id": f"{idx}",
+                "prompt": f"{prompt}",
+                "conversations": [
+                    {
+                        "from": "human",
+                        "value": "<image>\n <image>\nYou are given a text caption and two generated images based on that caption. Your task is to evaluate and compare these images based on two key criteria:\n1. Alignment with the Caption: Assess how well each image aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Image Quality: Examine the visual quality of each image, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both images using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Image 1 is better than Image 2.\", \"Image 2 is better than Image 1.\" and \"Both images are equally good.\".\nYour task is provided as follows:\nText Caption: [A harmoniously crafted glass sculpture, cinematically capturing the interplay of fire and ice, with dramatic lighting and deep, rich colors.]"
+                    },
+                    {
+                        "from": "gpt",
+                        "value": gpt_value
+                    }
+                ],
+                "images": [
+                    image1_path,
+                    image2_path
+                ]
+            }
+            idx += 1
+            save_data.append(template)
+            
+write_json("/inspire/qb-ilm/project/deepgen/wangdianyi-240107110022/BXH/RL_Data/OpenAI-4o_t2i_human_preference/train_data.json", save_data)

OpenAI-4o_t2i_human_preference/train_data.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1013a3175805d5d188e533c164d7e2f988e577cebf7cb7a320aab886951ad734
+size 19677435