ABDALLALSWAITI
/

aimaginedworlds

Model card Files Files and versions

ABDALLALSWAITI commited on Jan 7

Commit

2efbe65

·

verified ·

1 Parent(s): 2562af0

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ base_model: Tongyi-MAI/Z-Image-Turbo
 I want to share my experience training this LoRA—not just the final product, but the entire journey, because I believe transparency helps the community learn.
 ### 🚫 Attempt 1: The 1000-Image Dataset + V2 Adapter
-I started big. I thought more data = better results, so I gathered 1000 images and used the newest adapter:
 *   **Adapter:** `ostris/zimage_turbo_training_adapter V2`
 *   **Result:** Complete failure. The LoRA didn't capture the anime style at all. The outputs looked generic and lacked any personality from the training data.

 I want to share my experience training this LoRA—not just the final product, but the entire journey, because I believe transparency helps the community learn.
 ### 🚫 Attempt 1: The 1000-Image Dataset + V2 Adapter
+I started big. I thought more data = better results, so I gathered +1000 images do pro +1000 texts description and used the newest adapter:
 *   **Adapter:** `ostris/zimage_turbo_training_adapter V2`
 *   **Result:** Complete failure. The LoRA didn't capture the anime style at all. The outputs looked generic and lacked any personality from the training data.