Studio Ghibli style lora. I did not train it with audio. I used Seruva's dataset. I had to bucket the video by runtime length, but still worked out pretty decently. It is rank 16, I don't know if rank 32 would be better but this is still pretty decent. All examples are generated using the LTX2 distilled model.
Description
FAQ
Comments (1)
what is your setting i tried this Lora in ltx 2.5 it work well however in fast moving scene like the running girl i get too much distortion , please help
Details
Downloads
607
Platform
CivitAI
Platform Status
Available
Created
1/25/2026
Updated
9/29/2026
Deleted
-
Trigger Words:
studio ghibli style.
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.