LTX-2.3 Distilled LoRA Enhanced
Model description
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.
Usage
- Strength: 0.5 - 0.65
- Model: LTX-2.3 Dev | KJ - transformer_only (none-distilled checkpoints only)
- Stack it with your preferred N54W LoRA
Variants
| File | Size | Description |
|---|---|---|
| ltx-2.3-22b-distilled-lora-384-1.1_n4w.safetensors | 7.1 GB | same rank as the official |
| ltx-2.3-22b-distilled-lora-384-1.1_rank_128_n4w.safetensors | 2.4 GB | low VRAM, expect lower quality |
Expected Quality
When stacked with N54W LoRAs listed on Civitai and used with prompts and input images that follow LTX-2.3 prompting guidelines, roughly 6 out of 10 videos are usable. Body deformity and broken animation can still occur, this is standard LTX-2.3 behaviour. Prompt deviation from the input image increases the error rate.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 1,308
Model tree for rzgar/ltx-2.3-22b-distilled-lora-384-1.1-n4w
Base model
Lightricks/LTX-2.3