Update README.md

README.md

@@ -16,6 +16,18 @@ base_model: black-forest-labs/FLUX.1-dev
 until the next Diffusers pypi release, please install Diffusers from source and use [this PR](xxxxxx) to be able to use. 
 TODO: change when new version.
 
+## Checkpoint
+
+The training of union controlnet requires a significant amount of computational power. 
+The current release is only an alpha version checkpoint that has not been fully trained. 
+The beta version is in the training process. 
+We have conducted ablation studies that have demonstrated the validity of the code. 
+The open-source release of the alpha version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem; 
+it is common to encounter bad cases (please accept my apologies). 
+It is worth noting that we have found that even a fully trained Union model may not perform as well as specialized models, such as pose control. 
+However, as training progresses, the performance of the Union model will continue to approach that of specialized models.
+
+
 ## Control Mode
 | Control Mode | Description | Current Model Validity |
 |:------------:|:-----------:|:-----------:|
@@ -28,37 +40,27 @@ TODO: change when new version.
 |6|lq|🟢high|
 
 ### canny
-<img src="./images/image_demo_canny.jpg" width = "800" />
+<img src="./images/image_demo_canny.jpg" width = "300" />
 
 ### tile
-<img src="./images/image_demo_tile.jpg" width = "800" />
+<img src="./images/image_demo_tile.jpg" width = "300" />
 
 ### depth
-<img src="./images/image_demo_depth.jpg" width = "800" />
+<img src="./images/image_demo_depth.jpg" width = "300" />
 
 ### blur
-<img src="./images/image_demo_blur.jpg" width = "800" />
+<img src="./images/image_demo_blur.jpg" width = "300" />
 
 ### pose
-<img src="./images/image_demo_pose.jpg" width = "800" />
+<img src="./images/image_demo_pose.jpg" width = "300" />
 
 ### gray
-<img src="./images/image_demo_gray.jpg" width = "800" />
+<img src="./images/image_demo_gray.jpg" width = "300" />
 
 ### low quality
-<img src="./images/image_demo_lq.jpg" width = "800" />
-
+<img src="./images/image_demo_lq.jpg" width = "300" />
 
-## Checkpoint
 
-The training of union controlnet requires a significant amount of computational power. 
-The current release is only an alpha version checkpoint that has not been fully trained. 
-The beta version is in the training process. 
-We have conducted ablation studies that have demonstrated the validity of the code. 
-The open-source release of the alpha version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem; 
-it is common to encounter bad cases (please accept my apologies). 
-It is worth noting that we have found that even a fully trained Union model may not perform as well as specialized models, such as pose control. 
-However, as training progresses, the performance of the Union model will continue to approach that of specialized models.