Model card auto-generated by SimpleTuner

README.md

@@ -67,7 +67,7 @@ None
 - Steps: `20`
 - Sampler: `FlowMatchEulerDiscreteScheduler`
 - Seed: `42`
-- Resolution: `1408x768`
+- Resolution: `768x1280`
 - Skip-layer guidance: 
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
@@ -84,7 +84,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 250
+- Training steps: 500
 - Learning rate: 0.0004
   - Learning rate schedule: polynomial
   - Warmup steps: 100
@@ -130,7 +130,7 @@ You may reuse the base model text encoder for inference.
 ### or-256
 - Repeats: 10
 - Total number of images: 37
-- Total number of aspect buckets: 5
+- Total number of aspect buckets: 6
 - Resolution: 0.065536 megapixels
 - Cropped: False
 - Crop style: None
@@ -148,7 +148,7 @@ You may reuse the base model text encoder for inference.
 ### or-512
 - Repeats: 10
 - Total number of images: 37
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 6
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -166,7 +166,7 @@ You may reuse the base model text encoder for inference.
 ### or-768
 - Repeats: 10
 - Total number of images: 37
-- Total number of aspect buckets: 9
+- Total number of aspect buckets: 1
 - Resolution: 0.589824 megapixels
 - Cropped: False
 - Crop style: None
@@ -266,8 +266,8 @@ 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=1408,
-    height=768,
+    width=768,
+    height=1280,
     guidance_scale=4.0,
 ).images[0]
 image.save("output.png", format="PNG")