Update README.md
Browse files
README.md
CHANGED
|
@@ -10,12 +10,16 @@ tags:
|
|
| 10 |
|
| 11 |
<img src='resources/MERIDIQ_before_after_50_50.png' width='512'>
|
| 12 |
|
| 13 |
-
This is an experimental LoRA that adds bbox guided inpainting / editing to the Ideogram 4
|
| 14 |
model. It is a work in progress, so the files here are snapshots at different
|
| 15 |
points in time while I adjust training parameters and build a better dataset.
|
| 16 |
|
| 17 |
I currently get the most stable results with the [checkpoint at step 4000](https://huggingface.co/BitPoet/Ideogram4-Inpaint-LoRA/blob/main/IdoInpaint_2_00004000.safetensors) of the second training run.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Prerequisites
|
| 20 |
|
| 21 |
### Custom Node
|
|
|
|
| 10 |
|
| 11 |
<img src='resources/MERIDIQ_before_after_50_50.png' width='512'>
|
| 12 |
|
| 13 |
+
This is an early experimental LoRA that adds bbox guided inpainting / editing to the Ideogram 4
|
| 14 |
model. It is a work in progress, so the files here are snapshots at different
|
| 15 |
points in time while I adjust training parameters and build a better dataset.
|
| 16 |
|
| 17 |
I currently get the most stable results with the [checkpoint at step 4000](https://huggingface.co/BitPoet/Ideogram4-Inpaint-LoRA/blob/main/IdoInpaint_2_00004000.safetensors) of the second training run.
|
| 18 |
|
| 19 |
+
The dataset is very small, so do not expect any magic or precision. It is a starting point that
|
| 20 |
+
hopefully evolves over the next weeks as I prepare a bigger dataset and start over with training
|
| 21 |
+
with larger rank and finetuned parameters.
|
| 22 |
+
|
| 23 |
## Prerequisites
|
| 24 |
|
| 25 |
### Custom Node
|