.

README.md

@@ -2,3 +2,25 @@
 license: apache-2.0
 ---
 
+# Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
+
+### [Paper](https://arxiv.org/abs/) | [Code](https://github.com/viiika/Meissonic)
+
+
+## Introduction
+Meissonic is a non-autoregressive mask image modeling text-to-image synthesis model that can generate high-resolution images. It is designed to run on consumer graphics cards.
+
+## Usage
+
+Under Construction. Please check back later.
+
+## Citation
+If you find this work helpful, please consider citing:
+```bibtex
+@article{bai2024meissonic,
+  title={Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis},
+  author={Bai, Jinbin and Ye, Tian and Chow, Wei and Song, Enxin and Chen, Qing-Guo and Li, Xiangtai and Dong, Zhen and Zhu, Lei and Yan, Shuicheng},
+  journal={arXiv preprint arXiv},
+  year={2024}
+}
+```

model_index.json

@@ -2,7 +2,7 @@
   "_class_name": "Pipeline",
   "_diffusers_version": "0.30.2",
   "scheduler": [
-    "scheduler",
+    "src.scheduler",
     "Scheduler"
   ],
   "text_encoder": [
@@ -14,7 +14,7 @@
     "CLIPTokenizer"
   ],
   "transformer": [
-    "transformer",
+    "src.transformer",
     "Transformer2DModel"
   ],
   "vqvae": [

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a6a63bcfcb0d7cc9e2a687134ceb7cb83d0346285636ec8547e7ffa2bcd224
+size 708111984