Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ base_model:
|
|
| 9 |
This is a video-to-video IC-Lora for LTX 2.3, which is designed to remove credits and other text overlays from anime. It generalizes to live-action content quite well, too. It was trained on 100 paired clips from anime openings and endings.
|
| 10 |
|
| 11 |
## Usage
|
| 12 |
-
|
|
|
|
| 13 |
Lora strength 1.0 works well for standard credits. Increasing the strength to about 1.5 helps with larger or more stylized text.
|
|
|
|
| 14 |
LTX 2.3 tends to struggle with fast motion, so you may see a reduction in quality during fast moving parts.
|
|
|
|
| 9 |
This is a video-to-video IC-Lora for LTX 2.3, which is designed to remove credits and other text overlays from anime. It generalizes to live-action content quite well, too. It was trained on 100 paired clips from anime openings and endings.
|
| 10 |
|
| 11 |
## Usage
|
| 12 |
+
Trigger phrase (this should be your text prompt): removetext
|
| 13 |
+
|
| 14 |
Lora strength 1.0 works well for standard credits. Increasing the strength to about 1.5 helps with larger or more stylized text.
|
| 15 |
+
|
| 16 |
LTX 2.3 tends to struggle with fast motion, so you may see a reduction in quality during fast moving parts.
|