Update README.md

README.md

@@ -54,6 +54,11 @@ The model ControlNet trained on is our custom model.
   - trained with 921 generated images and MMPose preprocessing.
 - controllllite_v01032064e_sdxl_pose_anime_v2_500-1000.safetensors
   - trained with 1,415 generated images and MMPose preprocessing.
+- controllllite_v01016032e_sdxl_replicate_anime_0-500.safetensors
+  - trained with 896 generated image pairs, 1024x1024 and 2048x2048 (highres. fix-ed).
+  - Replicates the control image, mixed with the prompt, as possible as the model can.
+  - No preprocessor is required. Also works for img2img.
+  - Trained for 0-500 steps, but it seems to work 0-1000.
 
 
 # Samples
@@ -108,4 +113,8 @@ The model ControlNet trained on is our custom model.
 
 ![sample 10](./sample10.jpg)
 
+![replicate sample 1](./replicate_sample1.jpg)
+
+![replicate sample 2](./replicate_sample2.jpg)
+
 Sample images are generated by custom model.