Model card auto-generated by SimpleTuner

README.md

@@ -31,10 +31,10 @@ A pirate ship heading out to sea
 ## Validation settings
 - CFG: `7.5`
 - CFG Rescale: `0.0`
-- Steps: `20`
+- Steps: `10`
 - Sampler: `None`
 - Seed: `42`
-- Resolution: `512`
+- Resolution: `1024`
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
 
@@ -53,8 +53,8 @@ You may reuse the base model text encoder for inference.
 - Training steps: 5
 - Learning rate: 0.00105
 - Max grad norm: 0.01
-- Effective batch size: 8
-  - Micro-batch size: 8
+- Effective batch size: 1
+  - Micro-batch size: 1
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Prediction type: flow-matching
@@ -73,8 +73,8 @@ You may reuse the base model text encoder for inference.
 
 ### wikiart_s
 - Repeats: 1
-- Total number of images: 36
-- Total number of aspect buckets: 3
+- Total number of images: 40
+- Total number of aspect buckets: 7
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -100,10 +100,10 @@ pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps
 image = pipeline(
     prompt=prompt,
     negative_prompt=negative_prompt,
-    num_inference_steps=20,
+    num_inference_steps=10,
     generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
-    width=512,
-    height=512,
+    width=1024,
+    height=1024,
     guidance_scale=7.5,
 ).images[0]
 image.save("output.png", format="PNG")