Model card auto-generated by SimpleTuner

README.md

@@ -77,7 +77,7 @@ None
 - Steps: `20`
 - Sampler: `FlowMatchEulerDiscreteScheduler`
 - Seed: `42`
-- Resolution: `1024x1024`
+- Resolution: `896x1312`
 - Skip-layer guidance: 
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
@@ -93,10 +93,10 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 8
-- Training steps: 5000
-- Learning rate: 0.0003
-  - Learning rate schedule: polynomial
+- Training epochs: 9
+- Training steps: 5100
+- Learning rate: 0.0001
+  - Learning rate schedule: constant
   - Warmup steps: 200
 - Max grad norm: 2.0
 - Effective batch size: 3
@@ -167,7 +167,7 @@ You may reuse the base model text encoder for inference.
 ### frankpape-1536
 - Repeats: 5
 - Total number of images: 16
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 1
 - Resolution: 2.359296 megapixels
 - Cropped: False
 - Crop style: None
@@ -249,8 +249,8 @@ image = pipeline(
     prompt=prompt,
     num_inference_steps=20,
     generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
-    width=1024,
-    height=1024,
+    width=896,
+    height=1312,
     guidance_scale=3.0,
 ).images[0]
 image.save("output.png", format="PNG")