This model creates the "Joins the Battle" meme format. It is capable of understanding text, however it is still somewhat limited by the lackluster text rendering capabilities of LTX 2.3, so it may take more than one rendering to get the text right.
The primary triggerword is JTBCard, and you can specify the title, where the character name goes, the subtitle, which would normally say "Joins the Battle!," "Stops the competition," etc. along with the font colors and background. An example usage would be:
the woman crosses her arms then a JTBCard appears for her, the JTBCard title says "Tinkerbell" in white font, the JTBCard subtitle says "Joins the Battle!" in green font, The JTBCard background is a sky.California AB 2013 Training Data Disclosure
This LoRA was fine-tuned using visual data consisting of clips. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.
The dataset consists of 15 clips. This is the total used for training after low quality sets were culled. Dataset was collected/created in 2026.
Data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset.
This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.
Description
FAQ
Comments (6)
is this i2v only?
It was trained on I2V data, but due to the internal workings of LTX, it should also work for T2V videos.
@ReltivlyObjectv cool, works pretty well. wish ltx was better with spelling lol
@kronos1959777 just an idea, you could try generating the video, then taking the last frame, sending it through an edit model to fix the text and then use that as a last frame and generate again. Haven't tried it though
is there an English version?
The model is in English. The foreign-looking text that you see is just LTX not handling text rendering very well.