How is this MIT licensed?
What you've done is cool... but I do have one question...
From your readme:
https://huggingface.co/ScenemaAI/scenema-audio/blob/main/README.md?code=true#L39
Built on an audio diffusion transformer extracted from LTX 2.3's 22B parameter audiovisual model
The LTX License: https://github.com/Lightricks/LTX-2/blob/main/LICENSE#L24
LTX-2 Community License Agreement
"Derivatives of LTX-2" means all modifications to LTX-2, works
based on LTX-2, or any other model which is created or initialized
by transfer of patterns of the weights, parameters, activations or
output of LTX-2, to the other model, in order to cause the other
model to perform similarly to LTX-2, including – but not limited
to - distillation methods entailing the use of intermediate data
representations or methods based on the generation of synthetic
data by LTX-2 for training the other model.
Wouldn't an audio diffusion transformer extracted from LTX 2.3's 22B parameter audiovisual model be a Derivatives of LTX-2?
How are you able to change the license? Shouldn't this also be under the LTX-2 Community License?
You are correct! I've added clarification in the model card: inference and and all server code are under MIT license. Model checkpoints are under LTX-2 license.
You are correct! I've added clarification in the model card: inference and and all server code are under MIT license. Model checkpoints are under LTX-2 license.
Ah ok, that makes more sense. Thanks for clarifying. What you've done looks really cool, and I'd hate for your hard work to get taken down because of a license issue.