Model card auto-generated by SimpleTuner

README.md

@@ -85,11 +85,11 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 300
+- Training steps: 100
 - Learning rate: 1e-05
 - Max grad norm: 0.01
-- Effective batch size: 8
-  - Micro-batch size: 8
+- Effective batch size: 4
+  - Micro-batch size: 4
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Prediction type: flow-matching
@@ -101,8 +101,10 @@ You may reuse the base model text encoder for inference.
 - LyCORIS Config:
 ```json
 {
+    "bypass_mode": true,
     "algo": "lokr",
     "multiplier": 1.0,
+    "full_matrix": true,
     "linear_dim": 10000,
     "linear_alpha": 1,
     "factor": 12,
@@ -112,9 +114,6 @@ You may reuse the base model text encoder for inference.
         ],
         "module_algo_map": {
             "Attention": {
-                "factor": 12
-            },
-            "FeedForward": {
                 "factor": 6
             }
         }
@@ -125,7 +124,7 @@ You may reuse the base model text encoder for inference.
 ## Datasets
 
 ### screencaps-1024
-- Repeats: 10
+- Repeats: 0
 - Total number of images: 379
 - Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
@@ -133,6 +132,15 @@ You may reuse the base model text encoder for inference.
 - Crop style: None
 - Crop aspect: None
 - Used for regularisation data: No
+### screencaps-1024-crop
+- Repeats: 0
+- Total number of images: 379
+- Total number of aspect buckets: 1
+- Resolution: 1.048576 megapixels
+- Cropped: True
+- Crop style: random
+- Crop aspect: square
+- Used for regularisation data: No
 
 
 ## Inference