Model card auto-generated by SimpleTuner

README.md

@@ -20,7 +20,7 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'photo of @w4h'
+- text: '@w4h'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
@@ -33,7 +33,7 @@ This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https:/
 
 The main validation prompt used during training was:
 ```
-photo of @w4h
+@w4h
 ```
 
 
@@ -59,8 +59,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 0
-- Training steps: 500
+- Training epochs: 1
+- Training steps: 750
 - Learning rate: 8e-05
   - Learning rate schedule: polynomial
   - Warmup steps: 100
@@ -189,7 +189,7 @@ adapter_id = 'quzo/iwatch3'
 pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "photo of @w4h"
+prompt = "@w4h"
 
 
 ## Optional: quantise the model to save on vram.