LTX-2.5 Distilled LoRA Enhanced

txt2vid

Model description

Some generic text: The official distilled LoRA more or less acts as a negative strength when stacked with N54W LoRAs, fighting against their appearance and animation characteristics. This lora is an attempt to solve that conflict. Instead of counteracting, it works with N54W LoRAs, improving motion and appearance to varying degrees.

Files

File Size
ltx-2.5-22b-distilled-lora-450-rank_450_n4w.safetensors Download 8.90 GB
ltx-2.5-22b-distilled-lora-450-rank_384_n4w.safetensors Download 7.61 GB
ltx-2.5-22b-distilled-lora-450-rank_256_n4w.safetensors Download 5.10 GB

Companion LoRA | (Optional)

Usage

  • Strength: 0.55 - 0.65
  • Sampler: euler_ancestral | euler_cfg_pp
  • Model: LTX-2.5 Dev | int8-convrot (none-distilled checkpoints only)
  • Stack it with your preferred N54W LoRA:s

Download model

Download them in the Files & versions tab.

Downloads last month
2,966
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rzgar/ltx-2.5-22b-distilled-lora-450-enhanced-n4w

Adapter
(5)
this model
MiniMax H3 Video Generator 20 free credits · Text & image to video Try Free →