Update README.md

README.md

@@ -26,11 +26,16 @@ The goal is not to turn FLUX.2-dev into a deterministic renderer. Pixeled is sti
 
 ---
 
-## Recommended LoRA Scale
+## Recommended Settings
 
-The recommended LoRA scale for Pixeled is:
+The settings in json are:
 
-**`0.5`**
+{
+  "lora_scale": 0.5,
+  "guidance_scale": 5,
+  "seed": "random",
+  "num_inference_steps": 50
+}
 
 ```text
 FLUX.2-dev + Pixeled LoRA @ 0.5
@@ -38,9 +43,9 @@ FLUX.2-dev + Pixeled LoRA @ 0.5
 
 Pixeled is intended to enhance the prompt understanding of FLUX.2-dev rather than completely overpower the base model.
 
-At **0.5**, the base model can retain more of its original visual capabilities while Pixeled contributes its learned behavior for interpreting Pixelship's structured prompts.
+At these settings, the base model can retain more of its original visual capabilities while Pixeled contributes its learned behavior for interpreting Pixelship's structured prompts.
 
-Higher or lower values can still be experimented with, but **`0.5` is the recommended default**.
+Higher or lower values can still be experimented with, but this is the recommended.
 
 ---