This is an attempted extraction of DMD distillation in JoyAi Echo to use in other LTX models. It is not drop-in for standard workflows or a replacement for LTX Distilled Lora as-is. Right now it is the deltas with all audio connectors and blocks converted to base 384 distilled, then merged with rank 72_enery video blocks at ~%30 for first test. The exact amount and strategy is evolving but right now this works using Echo DMD sampling method and sigmas avaliable in 10S Nodes.
https://github.com/TenStrip/10S-Comfy-nodes
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for TenStrip/LTX2.3_DMD_Lora
Base model
Lightricks/LTX-2.3