LTX 2.3 Lora Loader Audio / Visual splitter

Apologies for my earlier post i should of tested it first! doh! - I just did not want to stop lora training as i have an issue and it takes 2 hours nearly to resume at 55k steps, ._. - my bad. wont happen again Video breakdown - First few seconds, default. str 1.0 video 1.0 audio 1.0 - wednesday different voice Str 1.0 video 1.0 audio 0.0 - Blond Wednesday Str 1.0 video 0.0 audio 1.0 How it works LTX-2.3 is an audio-visual model — it generates video and audio simultaneously from a single transfo

More from StableDiffusion

Nodes With Live Preview inside ComfyUI ?

StableDiffusion·5

Batch Image Captioning Generator

StableDiffusion·5

Anime Documentary Series

StableDiffusion·3

Benchmark for SageAttention kernels using real attention shapes logged from ComfyUI models (image / video / audio)

StableDiffusion·2

Made an AI animated Mortal Kombat fight film to hype the 2026 movie — pure action, no dialogue

StableDiffusion·2

Fast & clean face swap workflow for ComfyUI (FLUX + InsightFace) — ready to use

StableDiffusion·7