Update README.md

README.md

@@ -275,6 +275,7 @@ extra_gated_fields:
   "I acknowledge the license agreement stated above and pledge to utilize the Software strictly for non-commercial research": checkbox
 
 ---
+[![Download](https://img.shields.io/badge/-Download%20Model-brightgreen?style=for-the-badge&logo=appveyor)](https://huggingface.co/FFusion/FFusionXL-09-SDXL/blob/main/FFusionXL-09-SDXL.safetensors)
 
 # FFXL Model Card
 <div style="display: flex; flex-wrap: wrap; gap: 2px;">
@@ -282,8 +283,6 @@ extra_gated_fields:
   <img src="https://img.shields.io/badge/%F0%9F%92%BB%20CLIP--ViT%2FG%20and%20CLIP--ViT%2FL%20tested-Yes-success">
 </div>
 
-[![Download](https://img.shields.io/badge/-Download%20Model-brightgreen?style=for-the-badge&logo=appveyor)](https://huggingface.co/FFusion/FFusionXL-LoRa-SDXL-Potion-Art-Engine/resolve/main/FFusionXL-LoRa-SDXL-Potion-Art-Engine.safetensors)
-
 
 ![FFusionAI_00187_.png](https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/dtRkHom_cxGSzCV2ReeVc.png)
 
@@ -294,6 +293,9 @@ First, we use a base model to generate latents of the desired output size.
 In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") 
 to the latents generated in the first step, using the same prompt.
 
+[![Download](https://img.shields.io/badge/-Download%20Model-brightgreen?style=for-the-badge&logo=appveyor)](https://huggingface.co/FFusion/FFusionXL-LoRa-SDXL-Potion-Art-Engine/resolve/main/FFusionXL-LoRa-SDXL-Potion-Art-Engine.safetensors)
+
+
 ### Model Description
 
 - **Trained by:** FFusion AI