All future Int8 ConvRot files will go here

DMD - DMD lora baked at 1.0 strength unless otherwise stated. Using LTX2.3_DMD_hybrid_v2.

TFO - Transformer Only.

heur - Heuristic layer skipping. Skip layers with poor quantization characteristics.

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