Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,18 @@ All images gather from unsplash. Thanks to all creators who created the awesome
|
|
| 21 |
Update 20250314 \
|
| 22 |
Adding random selection training for beta. \
|
| 23 |
It ranfom selects noised factual or noised ground true to train. \
|
| 24 |
-
It is able to prevent the model degradation due to mis-aligned training objective.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
This is an Object Removal LoRA fine-tuned from Flux Fill Dev model. \
|
| 27 |
The lora is designed to remove objects from specified masked areas, making it useful for image editing tasks where unwanted objects need to be erased seamlessly. \
|
|
|
|
| 21 |
Update 20250314 \
|
| 22 |
Adding random selection training for beta. \
|
| 23 |
It ranfom selects noised factual or noised ground true to train. \
|
| 24 |
+
It is able to prevent the model degradation due to mis-aligned training objective.
|
| 25 |
+
<div align="center">
|
| 26 |
+
<table>
|
| 27 |
+
<tr>
|
| 28 |
+
<td align="center">
|
| 29 |
+
<p>Compare Between Alpha and Beta</p>
|
| 30 |
+
<img src="https://huggingface.co/lrzjason/ObjectRemovalFluxFill/resolve/main/ComfyUI_temp_npvyv_00007_.png" alt="Compare Between Alpha and Beta" width="800" />
|
| 31 |
+
</td>
|
| 32 |
+
</tr>
|
| 33 |
+
</table>
|
| 34 |
+
</div>
|
| 35 |
+
|
| 36 |
|
| 37 |
This is an Object Removal LoRA fine-tuned from Flux Fill Dev model. \
|
| 38 |
The lora is designed to remove objects from specified masked areas, making it useful for image editing tasks where unwanted objects need to be erased seamlessly. \
|