Model card auto-generated by SimpleTuner

README.md

@@ -16,7 +16,7 @@ widget:
     negative_prompt: ''''
   output:
     url: ./assets/image_0_0.png
-- text: 'a man is eating a donut'
+- text: 'anime illustraion of a group photo of ddadvege and ooozar together'
   parameters:
     negative_prompt: ''''
   output:
@@ -34,7 +34,7 @@ The main validation prompt used during training was:
 
 
 ```
-a man is eating a donut
+anime illustraion of a group photo of ddadvege and ooozar together
 ```
 
 ## Validation settings
@@ -58,8 +58,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 133
-- Training steps: 400
+- Training epochs: 66
+- Training steps: 200
 - Learning rate: 0.0001
 - Effective batch size: 1
   - Micro-batch size: 1
@@ -100,7 +100,7 @@ adapter_id = 'krigeta/flux-lora-training'
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "a man is eating a donut"
+prompt = "anime illustraion of a group photo of ddadvege and ooozar together"
 
 
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')