Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,27 @@ base_model:
|
|
| 17 |
# Unified-Reward-7B-v1.5
|
| 18 |
We are actively gathering feedback from the community to improve our models. **We welcome your input and encourage you to stay updated through our repository**!!
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
[2025/4/16] 🔥🔥 We updated the `UnifiedReward-7B-v1.5` by introducing pointwise scoring for generated images across three dimensions: alignment, coherence, and style, each rated on a continuous scale from 1 to 5.
|
| 21 |
|
| 22 |
1. **Alignment** quantifies how well an image matches its prompt.
|
|
|
|
| 17 |
# Unified-Reward-7B-v1.5
|
| 18 |
We are actively gathering feedback from the community to improve our models. **We welcome your input and encourage you to stay updated through our repository**!!
|
| 19 |
|
| 20 |
+
[2025/10/23] 🔥🔥🔥 We release **UnifiedReward-Edit**-[[3b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-3b)/[7b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-7b)/[32b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-32b)], a unified reward model for **both Text-to-Image and Image-to-Image generation** trained on approximately 700K unified image generation and editing reward data!!
|
| 21 |
+
For image editing reward task, our models support:
|
| 22 |
+
|
| 23 |
+
>1. Pairwise Rank — directly judge which of two edited images is better.
|
| 24 |
+
>
|
| 25 |
+
>2. Pairwise Score — assign a separate score to each image in a pair.
|
| 26 |
+
>
|
| 27 |
+
>3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality.
|
| 28 |
+
|
| 29 |
+
🚀 The image editing reward inference code is available at [`UnifiedReward-Edit/`](https://github.com/CodeGoat24/UnifiedReward/tree/main/UnifiedReward-Edit) directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from [EditScore](https://huggingface.co/datasets/EditScore/EditScore-Reward-Data) and [EditReward](https://huggingface.co/datasets/TIGER-Lab/EditReward-Data) and will be released soon. We sincerely appreciate all contributors!!
|
| 30 |
+
|
| 31 |
+
[2025/9/25] 🔥🔥🔥 We release **UnifiedReward-2.0**-qwen-[[3b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-3b)/[7b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-7b)/[32b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-32b)/[72b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-72b)].
|
| 32 |
+
This version introduces several new capabilities:
|
| 33 |
+
>
|
| 34 |
+
>1. **Pairwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence_**, **_Style_** dimensions.
|
| 35 |
+
>
|
| 36 |
+
>2. **Pointwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence/Physics_**, **_Style_** dimensions.
|
| 37 |
+
>
|
| 38 |
+
The added inference code is available at [`inference_qwen/UnifiedReward-2.0-inference`](https://github.com/CodeGoat24/UnifiedReward/tree/main/inference_qwen/UnifiedReward-2.0-inference) directory. The newly added training data has been released [here](https://huggingface.co/datasets/CodeGoat24/UnifiedReward-2.0-T2X-score-data) 😊.
|
| 39 |
+
|
| 40 |
+
|
| 41 |
[2025/4/16] 🔥🔥 We updated the `UnifiedReward-7B-v1.5` by introducing pointwise scoring for generated images across three dimensions: alignment, coherence, and style, each rated on a continuous scale from 1 to 5.
|
| 42 |
|
| 43 |
1. **Alignment** quantifies how well an image matches its prompt.
|