Cinematic finetune

cinematique_lora_13b_landscape_768_576_121 is a LoRA checkpoint fine-tuned for cinematic landscape generation at 768×576 resolution with 121 frames (~5 seconds), built on top of a 13B base model.

Lora config

  rank: 128
  alpha: 128
  dropout: 0.0
  target_modules:
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"

license: apache-2.0

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train NirZabariLTX/cinematic-finetune