Flux-2-pro_t2i_human_preference
收藏魔搭社区2025-12-05 更新2025-12-06 收录
下载链接：
https://modelscope.cn/datasets/Rapidata/Flux-2-pro_t2i_human_preference
下载链接
链接失效反馈官方服务：
资源简介：
<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;
}
.link-container {
padding: 10px;
text-align: center;
border: 1px solid #000000;
border-radius: .25rem;
}
.image{
margin:0 auto;
}
</style>
# Rapidata Flux 2 Pro 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 ~400'000 human responses from over ~50'000 individual annotators, collected in less than 7h using the [Rapidata Python API](https://docs.rapidata.ai), accessible to anyone and ideal for large scale evaluation.
Evaluating Flux 2 Pro (version from 25.11.25) 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 ❤️
To add your own model to the benchmark send us an e-mail at: jason@rapidata.ai
## Overview
The evaluation consists of 1v1 comparisons between Flux 2 Pro (version from 24.7.2025) and 18 other models:
- 4o
- Flux-1-pro
- Flux-1.1-pro
- imagen 4 ultra
- Aurora
- Imagen-3
- DALL-E 3
- Midjourney-5.2
- Frames-23-1-25
- Stable Diffusion 3
- Janus-7b.
- hidream-l1-full
- Recraft V2
- Ideogram V2
- halfmoon-4-4-25
- Lumina-15-2-25
- Imagen 4 Ultra 20.5.25
- Imagen 4 Ultra 24.7.25
- Recraft v3
- Hunyuan Image 2.1
## 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>The cracked rectangle was leaning against the glossy cylinder and the peeling triangle.</q>
</div>
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro </h3>
<div class="score-percentage">Score: 100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/vo7NdtZ6V1x0hVD_piOle.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Seedream 3 </h3>
<div class="score-percentage">Score: 0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/psHazJXGQ6IN1rOakPZDO.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="text-center">
<q>The square coaster was next to the circular glass.</q>
</div>
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro </h3>
<div class="score-percentage">Score: 0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/I5kI3eurHZSqWRZay-su0.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">4o </h3>
<div class="score-percentage">Score: 100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/Fj8QL93Nokm_LgJoAtlSk.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">Flux 2 Pro </h3>
<div class="score-percentage">Glitch Rating: 0%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/cdR8kXoWeJOFhwsJSE8-8.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Flux 1 Pro </h3>
<div class="score-percentage">Glitch Rating: 100%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/QvFsh1iMX6sBBc_xox_gG.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro </h3>
<div class="score-percentage">Glitch Rating: 100%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/5kvf9hSGUApakuMaTMTwu.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Halfmoon 4 </h3>
<div class="score-percentage">Glitch Rating: 0%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/WzoqlDL-SDBYTTwOR1bAF.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">Flux 2 Pro </h3>
<div class="score-percentage">Score: 100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/LOb8N1QYMMrgwK3Jg4KQj.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/672b7d79fd1e92e3c3567435/yT5LbhwZrOmU4AeeXE49c.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro </h3>
<div class="score-percentage">Score: 0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/6wfRY8v6svdIS85uUmvaB.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Lumina </h3>
<div class="score-percentage">Score: 100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/jQxurLywO5lYziJ82bVl2.jpeg" width=500>
</div>
</div>
</div>
</div>
## Benchmark
<a href="https://app.rapidata.ai/mri/benchmarks/686e5afa75adbe4a56f90549">
<div class="link-container">
<div>
Check out the Benchmark!
</div>
<img class="image" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/HyeJQ_Pt_K4jkySp55IGO.png" alt="Audio Benchmark">
</div>
</a>
## 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.
# Rapidata Flux 2 Pro 偏好数据集
<a href="https://www.rapidata.ai">
<img src="https://cdn-uploads.huggingface.co/production/uploads/66f5624c42b853e73e0738eb/jfxR79bOztqaC6_yNNnGU.jpeg" width="400" alt="数据集可视化">
</a>
本**文本到图像（Text-to-Image, T2I）**数据集收录了来自超5万名独立标注者的近40万条人类反馈结果，仅用不到7小时便通过[Rapidata Python API](https://docs.rapidata.ai)完成采集，全平台公开且适配大规模评估场景。
本次评估针对Flux 2 Pro（2025年11月25日版本）从三大维度展开：偏好性、连贯性与对齐性。
可前往我们的[官方网站](https://www.rapidata.ai/benchmark)查看最新的模型排名。
若您从本数据集获益并希望未来获取更多同类资源，欢迎为其点赞 ❤️
若希望将您的模型加入基准测试，请发送邮件至：jason@rapidata.ai
## 概述
本次评估采用Flux 2 Pro（2025年7月24日版本）与其余18款模型进行1v1对比，参与对比的模型包括：
- 4o
- Flux-1-pro
- Flux-1.1-pro
- imagen 4 ultra
- Aurora
- Imagen-3
- DALL-E 3
- Midjourney-5.2
- Frames-23-1-25
- Stable Diffusion 3
- Janus-7b
- hidream-l1-full
- Recraft V2
- Ideogram V2
- halfmoon-4-4-25
- Lumina-15-2-25
- Imagen 4 Ultra 20.5.25
- Imagen 4 Ultra 24.7.25
- Recraft v3
- Hunyuan Image 2.1
## 对齐性
对齐分数用于量化生成图像与输入提示词的匹配程度。用户被问及的问题为：「哪张图像更贴合给定描述？」
<div class="vertical-container">
<div class="container">
<div class="text-center">
<q>开裂的矩形倚靠在光滑的圆柱体与剥落的三角形旁。</q>
</div>
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">得分：100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/vo7NdtZ6V1x0hVD_piOle.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Seedream 3</h3>
<div class="score-percentage">得分：0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/psHazJXGQ6IN1rOakPZDO.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="text-center">
<q>方形杯垫紧邻圆形玻璃杯。</q>
</div>
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">得分：0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/I5kI3eurHZSqWRZay-su0.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">4o</h3>
<div class="score-percentage">得分：100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/Fj8QL93Nokm_LgJoAtlSk.jpeg" width=500>
</div>
</div>
</div>
</div>
## 连贯性
连贯性分数用于衡量生成图像是否具备逻辑自洽性，且无伪影或视觉瑕疵。在不查看原始提示词的前提下，用户被问及的问题为：「哪张图像存在更多瑕疵，且更有可能是AI生成的？」
<div class="vertical-container">
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">瑕疵评级：0%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/cdR8kXoWeJOFhwsJSE8-8.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Flux 1 Pro</h3>
<div class="score-percentage">瑕疵评级：100%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/QvFsh1iMX6sBBc_xox_gG.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">瑕疵评级：100%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/5kvf9hSGUApakuMaTMTwu.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Halfmoon 4</h3>
<div class="score-percentage">瑕疵评级：0%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/WzoqlDL-SDBYTTwOR1bAF.jpeg" width=500>
</div>
</div>
</div>
</div>
## 偏好性
偏好性分数用于反映参与者对每张图像的视觉好感度，与提示词无关。用户被问及的问题为：「你更偏好哪张图像？」
<div class="vertical-container">
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">得分：100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/LOb8N1QYMMrgwK3Jg4KQj.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Stable Diffusion 3</h3>
<div class="score-percentage">得分：0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/yT5LbhwZrOmU4AeeXE49c.jpeg" width=500>
</div>
</div>
</div>
<div class="container">
<div class="image-container">
<div>
<h3 class="score-amount">Flux 2 Pro</h3>
<div class="score-percentage">得分：0%</div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/6wfRY8v6svdIS85uUmvaB.jpeg" width=500>
</div>
<div>
<h3 class="score-amount">Lumina</h3>
<div class="score-percentage">得分：100%</div>
<img style="border: 5px solid #18c54f;" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/jQxurLywO5lYziJ82bVl2.jpeg" width=500>
</div>
</div>
</div>
</div>
## 基准测试
<a href="https://app.rapidata.ai/mri/benchmarks/686e5afa75adbe4a56f90549">
<div class="link-container">
<div>
前往查看基准测试！
</div>
<img class="image" src="https://cdn-uploads.huggingface.co/production/uploads/672b7d79fd1e92e3c3567435/HyeJQ_Pt_K4jkySp55IGO.png" alt="音频基准测试">
</div>
</a>
## 关于Rapidata
Rapidata的技术使大规模人类反馈采集比以往任何时候都更快捷、更易用。请访问[rapidata.ai](https://www.rapidata.ai/)了解更多关于我们如何革新AI开发领域的人类反馈采集方式的信息。
提供机构：
maas
创建时间：
2025-12-03
