Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,7 @@ As for the trigger words, the six characters can be prompted with
|
|
| 22 |
`TenkawaNayuta` is tagged but she appears in fewer than 10 images so don't expect any good result.
|
| 23 |
There are also three different styles trained into the model: `aniscreen`, `edstyle`, and `megazine` (yes, typo).
|
| 24 |
As usual you can get multiple-character imagee but starting from 4 it is difficult.
|
|
|
|
| 25 |
|
| 26 |
In the following images are shown the generations of different checkpoints.
|
| 27 |
The default one is that of step 22828, but all the checkpoints starting from step 9969 can be found in the `checkpoints` directory.
|
|
@@ -69,5 +70,6 @@ The following configuration is used
|
|
| 69 |
- batch size 8
|
| 70 |
- conditional dropout 0.08
|
| 71 |
- change beta scheduler from `scaler_linear` to `linear` in `config.json` of the scheduler of the model
|
|
|
|
| 72 |
|
| 73 |
I trained for two epochs wheareas the default release model was trained for 22828 steps as mentioned above.
|
|
|
|
| 22 |
`TenkawaNayuta` is tagged but she appears in fewer than 10 images so don't expect any good result.
|
| 23 |
There are also three different styles trained into the model: `aniscreen`, `edstyle`, and `megazine` (yes, typo).
|
| 24 |
As usual you can get multiple-character imagee but starting from 4 it is difficult.
|
| 25 |
+
By the way, the model is trained at clip skip 1.
|
| 26 |
|
| 27 |
In the following images are shown the generations of different checkpoints.
|
| 28 |
The default one is that of step 22828, but all the checkpoints starting from step 9969 can be found in the `checkpoints` directory.
|
|
|
|
| 70 |
- batch size 8
|
| 71 |
- conditional dropout 0.08
|
| 72 |
- change beta scheduler from `scaler_linear` to `linear` in `config.json` of the scheduler of the model
|
| 73 |
+
- clip skip 1
|
| 74 |
|
| 75 |
I trained for two epochs wheareas the default release model was trained for 22828 steps as mentioned above.
|