Update README.md

README.md

@@ -3,12 +3,15 @@ license: apache-2.0
 ---
 
 # Flux-Mini
+
+A distilled Flux-dev model for efficient text-to-image generation
+
+
 <div align="center">
 <img src="flux_distill-flux-mini-teaser.jpg" width="800" alt="Teaser image">
 </div>
 
 
-A distilled Flux-dev model for efficient text-to-image generation
 
 
 
@@ -17,10 +20,10 @@ To bridge this gap, we distilled the **12B** `Flux-dev` model into a **3.2B** `F
 Specifically, we prune the original `Flux-dev` by reducing its depth from `19 + 38` (number of double blocks and single blocks) to `5 + 10`. 
 The pruned model is further tuned with denoising and feature alignment objectives on a curated image-text dataset.
 
-We empeirically found that different blocks has different impact on the generation quality, thus we initialize the student model with several most important blocks. 
-The distillation process consists of three objectives: the denoise loss, the output alignment loss and the feature alignment loss. 
-The feature aligement loss is designed in a way such that the output of `block-x` in the student model is encouraged to match that of `block-4x` in the teacher model. 
-The distillation process is performed with `512x512` laion images recaptioned with `Qwen-VL` in the first stage for `90k steps`, 
+We empirically found that different blocks have different impacts on the generation quality, thus we initialize the student model with several most important blocks. 
+The distillation process consists of three objectives: the denoise loss, the output alignment loss as well as the feature alignment loss. 
+The feature alignment loss is designed in a way such that the output of `block-x` in the student model is encouraged to match that of `block-4x` in the teacher model. 
+The distillation process is performed with `512x512` Laion images recaptioned with `Qwen-VL` in the first stage for `90k steps`, 
 and `1024x1024` images generated by `Flux` using the prompts in `JourneyDB` with another `90k steps`.