Model card auto-generated by SimpleTuner

README.md

@@ -18,21 +18,26 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'unconditional (blank prompt)'
+- text: 'A cute, anime-style character with cat ears and silver hair stands in a cozy kitchen, holding a large pillow in a playful, pouting pose, anime in real life'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
-    url: ./assets/image_1_1.png
-- text: 'A photo-realistic image of a cat'
+    url: ./assets/image_1_0.png
+- text: 'A cute anime character sits at a table with delicious dishes of fried chicken and rice, surrounded by drinks and a busy street view outside, anime in real life'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_2_0.png
-- text: 'A photo-realistic image of a cat'
+- text: 'A girl with long blonde hair sleeps peacefully on a couch, with a foggy city view visible through the window, anime in real life'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'A cozy room with a bed and soft pillows, featuring an animated character lying happily on the blanket, surrounded by simple decor, anime in real life'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
-    url: ./assets/image_3_1.png
+    url: ./assets/image_4_0.png
 ---
 
 # simpletuner-lora
@@ -40,13 +45,13 @@ widget:
 This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium).
 
 
-The main validation prompt used during training was:
+No validation prompt was used during training.
 
 
 
-```
-A photo-realistic image of a cat
-```
+
+None
+
 
 ## Validation settings
 - CFG: `3.0`
@@ -54,7 +59,7 @@ A photo-realistic image of a cat
 - Steps: `20`
 - Sampler: `None`
 - Seed: `42`
-- Resolutions: `1024x1024,1280x768`
+- Resolution: `1024x1024`
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
 
@@ -69,9 +74,9 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 25
-- Training steps: 4500
-- Learning rate: 0.0001
+- Training epochs: 2
+- Training steps: 500
+- Learning rate: 5e-05
 - Max grad norm: 0.01
 - Effective batch size: 1
   - Micro-batch size: 1
@@ -135,7 +140,7 @@ lora_scale = 1.0
 wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
 wrapper.merge_to()
 
-prompt = "A photo-realistic image of a cat"
+prompt = "An astronaut is riding a horse through the jungles of Thailand."
 negative_prompt = 'blurry, cropped, ugly'
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = pipeline(