[KongchangAI]
ModelLTX Video 2.3

LTX-2.3

A video generation diffusion model capable of producing high-quality video clips. It supports FP8 weight quantization for deployment, optimizing GPU memory usage and inference speed.

Timeline (last 90 days)

Oct 13

Wan2.2-TI2V-5B, LTX-2, and LTX-2.3 can animate images by setting the Start frame on the same loaded model.

Unverified50%
Oct 8

The user had previously generated a similar clip using LTX-2.3 with the Union Control LoRA.

Unverified50%
Sep 28

LTX-2.3 video clip generation speed has increased by approximately 4.5×, thanks to distilled sampling, compilation fixes, and hosted FP8 weights.

Unverified50%

All Facts (3)

Source Articles