LTX-2.3 Dev Audio+Image To Video (GGUF)

base workflow for Audio+Image to video for Dev model. LOW VRAM as possible.

can also generate text to video with audio reference. (switch red boolean node to TRUE)

i suggest leaving the prompt alone unless you want to prompt for a specific motion or action to occur.

prompt:

" Transform this static image into a high-quality video with with realistic facial expressions and realistic motion.

Perfect lip-sync to the attached audio. "

FILES:

OPTIONAL Kijais fp8 Scaled (requires load diffusion model node instead of unet loader node and replaces the gguf entirely. )

style="color:rgb(250, 82, 82)">DEV gguf (distilled ggufs are in the repo as well)

style="color:rgb(250, 82, 82)">Gemma 3_12B FP4 text encoder

style="color:rgb(250, 82, 82)">Audio VAE

style="color:rgb(250, 82, 82)">Video VAE

style="color:rgb(250, 82, 82)">Text Projection text encoder

style="color:rgb(250, 82, 82)">Distill Lora

style="color:rgb(250, 82, 82)">Upscaler

data-youtube-video>