Add pipeline tag and library name metadata

README.md

@@ -1,5 +1,7 @@
 ---
 license: mit
+library_name: diffusers
+pipeline_tag: text-to-image
 tags:
 - diffusion
 - transformers
@@ -25,9 +27,9 @@ tags:
 _Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)_
 
 ## Abstract
-Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. However, existing approaches typically append auxiliary control modules or stitch together separate uni-modal networks.
+Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. However, most existing approaches typically extend pre-trained text-to-image pipelines by appending auxiliary control modules or stitching together separate uni-modal networks.
 
-We introduce **MMFace-DiT**, a unified dual-stream diffusion transformer engineered for synergistic multimodal face synthesis. Its core novelty lies in a dual-stream transformer block that processes spatial (mask/sketch) and semantic (text) tokens in parallel, deeply fusing them through a shared **Rotary Position-Embedded (RoPE) Attention** mechanism. Furthermore, a novel **Modality Embedder** enables a single cohesive model to dynamically adapt to varying spatial conditions without retraining. MMFace-DiT achieves a 40% improvement in visual fidelity and prompt alignment over five state-of-the-art multimodal face generation models.
+We introduce **MMFace-DiT**, a unified dual-stream diffusion transformer engineered for synergistic multimodal face synthesis. Its core novelty lies in a dual-stream transformer block that processes spatial (mask/sketch) and semantic (text) tokens in parallel, deeply fusing them through a shared **Rotary Position-Embedded (RoPE) Attention** mechanism. Furthermore, a novel **Modality Embedder** enables a single cohesive model to dynamically adapt to varying spatial conditions without retraining. MMFace-DiT achieves a 40% improvement in visual fidelity and prompt alignment over six state-of-the-art multimodal face generation models, establishing a flexible new paradigm for end-to-end controllable generative modeling.
 
 ## Repository Contents
 This repository contains the trained model checkpoints for MMFace-DiT. The models are provided for both Diffusion and Rectified Flow Matching (Flow) paradigms across different resolutions.
@@ -54,7 +56,7 @@ python sample_flow.py \
   --guidance_scale 7.5
 ```
 
-## Citation:
+## Citation
 If you find this work helpful for your research, please cite our CVPR paper:
 
 ```bibtex