Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,7 @@ pipeline_tag: image-to-image
|
|
| 25 |
<a href="https://huggingface.co/CSU-JPG/FlowInOne" style="text-decoration: none;">🤗 Model</a>
|
| 26 |
</p>
|
| 27 |
</div>
|
|
|
|
| 28 |
## About
|
| 29 |
We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm.
|
| 30 |
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.
|
|
|
|
| 25 |
<a href="https://huggingface.co/CSU-JPG/FlowInOne" style="text-decoration: none;">🤗 Model</a>
|
| 26 |
</p>
|
| 27 |
</div>
|
| 28 |
+
|
| 29 |
## About
|
| 30 |
We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm.
|
| 31 |
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.
|