BitPoet commited on
Commit
7eb04d0
·
verified ·
1 Parent(s): 3714332

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
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