Update README.md
Browse files
README.md
CHANGED
|
@@ -32,4 +32,13 @@ This vision-centric formulation naturally eliminates cross-modal alignment bottl
|
|
| 32 |
Extensive experiments demonstrate that FlowInOne achieves **state-of-the-art performance across all unified generation tasks**, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.
|
| 33 |
|
| 34 |
## 🧪 Usage
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
Our training and inference scripts are now available on [GitHub](https://github.com/CSU-JPG/FlowInOne)!
|
|
|
|
| 32 |
Extensive experiments demonstrate that FlowInOne achieves **state-of-the-art performance across all unified generation tasks**, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.
|
| 33 |
|
| 34 |
## 🧪 Usage
|
| 35 |
+
you can download the model weights and model preparation
|
| 36 |
+
```bash
|
| 37 |
+
wget https://huggingface.co/CSU-JPG/FlowInOne/resolve/main/flowinone_256px.pth
|
| 38 |
+
|
| 39 |
+
```
|
| 40 |
+
you can download the dataset examples
|
| 41 |
+
```bash
|
| 42 |
+
|
| 43 |
+
```
|
| 44 |
Our training and inference scripts are now available on [GitHub](https://github.com/CSU-JPG/FlowInOne)!
|