Model card auto-generated by SimpleTuner

README.md

@@ -33,7 +33,7 @@ A smiling girl whose name is Seoyeon.
 - Steps: `30`
 - Sampler: `None`
 - Seed: `42`
-- Resolution: `1024`
+- Resolution: `512`
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
 
@@ -50,11 +50,11 @@ You may reuse the base model text encoder for inference.
 
 - Training epochs: 1999
 - Training steps: 2000
-- Learning rate: 1.0
+- Learning rate: 1e-05
 - Effective batch size: 4
   - Micro-batch size: 1
-  - Gradient accumulation steps: 4
-  - Number of GPUs: 1
+  - Gradient accumulation steps: 2
+  - Number of GPUs: 2
 - Prediction type: flow-matching
 - Rescaled betas zero SNR: False
 - Optimizer: AdamW, stochastic bf16
@@ -70,9 +70,9 @@ You may reuse the base model text encoder for inference.
 
 ### Seoyeon
 - Repeats: 0
-- Total number of images: 4
+- Total number of images: ~4
 - Total number of aspect buckets: 1
-- Resolution: 1 megapixels
+- Resolution: 512 px
 - Cropped: True
 - Crop style: center
 - Crop aspect: square
@@ -98,8 +98,8 @@ image = pipeline(
     prompt=prompt,
     num_inference_steps=30,
     generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
-    width=1024,
-    height=1024,
+    width=512,
+    height=512,
     guidance_scale=3.5,
 ).images[0]
 image.save("output.png", format="PNG")