Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
| Date | Stars |
|---|---|
| 2026-07-24 | 1694 |
| 2026-07-25 | 1694 |
| 2026-07-28 | 1695 |
| 2026-07-30 | 1695 |
| 2026-07-31 | 1696 |
| 2026-08-06 | 1696 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.06%/day
# ImageReward
<p align="center">
📃 <a href="https://arxiv.org/abs/2304.05977" target="_blank">Paper</a> • 🖼 <a href="https://huggingface.co/datasets/THUDM/ImageRewardDB" target="_blank">Dataset</a> • 🌐 <a href="https://zhuanlan.zhihu.com/p/639494251" target="_blank">中文博客</a> • 🤗 <a href="https://huggingface.co/THUDM/ImageReward" target="_blank">HF Repo</a> • 🐦 <a href="https://twitter.com/thukeg" target="_blank">Twitter</a> <br>
</p>
🔥🔥 **News!** ```2024/12/31```: We released the **next generation of model, [VisionReward](https://github.com/THUDM/VisionReward)**, which is a fine-grained and multi-dimensional reward model for stable RLHF for visual generation (text-to-image / text-to-video)!
🔥 **News!** ```2023/9/22```: The paper of ImageReward is accepted by NeurIPS 2023!
**ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation**
ImageReward is the first general-purpose text-to-image human preference RM, which is trained on in total **137k pairs of expert comparisons**, outperforming existing text-image scoring methods, such as CLIP (by 38.6%), Aesthetic (by 39.6%), and BLIP (by 31.6%), in terms of understanding human preference in text-to-image synthesis.
Additionally, we introduce Reward Feedback Learning (ReFL) for direct optimizing a text-to-image diffusion model using ImageReward. ReFL-tuned Stable Diffusion wins against untuned version by 58.4% in human evaluation.
Both ImageReward and ReFL are all packed up to Python `image-reward` package now!
[](https://pypi.org/project/image-reward/) [](https://pepy.tech/project/image-reward)
Try `image-reward` package in only 3 lines of code for ImageReward scoring!
```python
# pip install image-reward
import ImageReward as RM
model = RM.load("ImageReward-v1.0")
rewards = model.score("<prompt>", ["<img1_obj_or_path>", "<img2_obj_or_path>", ...])
```
Try `image-reward` package in only 4 lines of code for ReFL fine-tuning!
```python
# pip install image-reward
# pip install diffusers==0.16.0 accelerate==0.16.0 datasets==2.11.0
from ImageReward import ReFL
args = ReFL.parse_args()
trainer = ReFL.Trainer("CompVis/stable-diffusion-v1-4", "data/refl_data.json", args=args)
trainer.train(args=args)
```
If you find `ImageReward`'s open-source effort useful, please 🌟 us to encourage our following developement!
<p align="center">
<img src="figures/ImageReward.jpg" width="700px">
</p>
- [ImageReward](#imagereward)
- [Quick Start](#quick-start)
- [Install Dependency](#install-dependency)
- [Example Use](#example-use)
- [ReFL](#refl)
- [Install Dependency](#install-dependency-1)
- [Example Use](#example-use-1)
- [Demos of ImageReward and ReFL](#demos-of-imagereward-and-refl)
- [Training code for ImageReward](#training-code-for-imagereward)
- [Integration into Stable Diffusion Web UI](#integration-into-stable-diffusion-web-ui)
- [Features](#features)
- [Score generated images and append to image information](#score-generated-images-and-append-to-image-information)
- [Usage](#usage)
- [Demo video](#demo-video)
- [Automatically filter out images with low scores](#automatically-filter-out-images-with-low-scores)
- [Usage](#usage-1)
- [Demo video](#demo-video-1)
- [View the scores of images that have been scored](#view-the-scores-of-images-that-have-been-scored)
- [Usage](#usage-2)
- [Example](#example)
- [Other Features](#other-features)
- [Memory Management](#memory-management)
- [FAQ](#faq)
- [Reproduce Experiments in Table 1](#reproduce-experiments-in-table-1)
- [Reproduce Experiments in Table 3](#reproduce-experiments-in-table-3)
- [Citation](#citation)
## Quick Start
### Install Dependency
We have integrated the whole repository to a single python package `image-reward`. Following the commands below to prepare the enviExcerpt of 13,064 characters
Read on GitHub
Jiazheng Xu · Tsinghua University, KEG Group · China
25
Shaw · Tsinghua University · China
7
Shawn/Yuxuan Tong · ByteDance Seed · China
5
1
1
Yuxuan Zhang · Z.ai · China
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f7870d7d93dfea32, topic:diffusion-models, desc:text-to-image, readme:text-to-image
matched fp:f7870d7d93dfea32, topic:rlhf, readme:fine-tuning, readme:fine tuning