Image-to-Image
English
Junc1i commited on
Commit
5cb60dc
·
verified ·
1 Parent(s): 22ce776

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
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.