LiconStudio
/

Ltx2.3-VBVR-lora-I2V

video-generation

video-reasoning

logical-reasoning

Model card Files Files and versions

LiconStudio commited on May 13

Commit

584c96e

·

verified ·

1 Parent(s): 43750f5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -92,7 +92,7 @@ This LoRA adapter enhances the base LTX-2 model for production video generation
 | Max Grad Norm | 1.0 |
 | Target Modules | `to_q`, `to_k`, `to_v`, `to_out.0`, `ff.net.0.proj`, `ff.net.2` |
-### Stage 3: General + Hard Reasoning (490K)
 | Config | Value |
 |--------|-------|
 | Dataset | 240K general videos + 150K high-difficulty reasoning videos |

 | Max Grad Norm | 1.0 |
 | Target Modules | `to_q`, `to_k`, `to_v`, `to_out.0`, `ff.net.0.proj`, `ff.net.2` |
+### Stage 3: General + Hard Reasoning (390K)
 | Config | Value |
 |--------|-------|
 | Dataset | 240K general videos + 150K high-difficulty reasoning videos |