Update README.md


README.md

@@ -6,12 +6,13 @@ tags:
 - looner,
 - balloon_pop
 ---
-# ◄Experimental► Looner concept for SDXL
+# ◄Experimental► Looner concept for SDXL (V0.1)
 
 <!-- Provide a quick summary of what the model is/does. -->
 
 This is an attempt to train a new concept using SDXL. 
-A 3000-step lora was trained at rank 2 and alpha 0.5 in an attempt to minimise style transfer, yet the model requires very high stregth to work (>0.9), taking a hit in quality.
+A 3000-step lora was trained at rank 2 and alpha 0.5 in an attempt to minimise style transfer, yet the model requires very high stregth to work (>0.9), taking a hit in quality
+Model was trained on a single caption, "a person is blowing a large balloon". Further experimentation using other captioning methods and different rank/alpha values are underway.
 
 
 ## Bias, Risks, and Limitations
@@ -21,8 +22,15 @@ A 3000-step lora was trained at rank 2 and alpha 0.5 in an attempt to minimise s
 The model cannot reproduce the concept accurately
 Due to high lora strength, even at rank 2, style transfer occurs. 
 
+![00071-576851394.png](https://cdn-uploads.huggingface.co/production/uploads/646d56d34220471ca0c74197/b1TpAVRgbRe5ZbCqNq31k.png)
+![00099-2133353150.png](https://cdn-uploads.huggingface.co/production/uploads/646d56d34220471ca0c74197/bugrH1SrTlvNZbGaZlCQu.png)
+![00125-2352500702.png](https://cdn-uploads.huggingface.co/production/uploads/646d56d34220471ca0c74197/K2TACHAWhOcL9C7qksMIr.png)
+![00152-3784117391.png](https://cdn-uploads.huggingface.co/production/uploads/646d56d34220471ca0c74197/l-xeHv4WP9fmabLbM20i_.png)
+![00404-2466931544.png](https://cdn-uploads.huggingface.co/production/uploads/646d56d34220471ca0c74197/pFa8P_mZ5Z7vXJEpCa-Eh.png)
+
 ### Recommendations
 
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
 Model should be loaded at clip skip 1 and stregth above 0.8 on most checkpoints.
+