DemonAlone/LTX-2.3, simple workflow. T2V, image (multiply) reference, external audio support, V2V (IC lora + depth mask) [DEPRECATE

Pretty simple workflow for LTXV. There is no prompt enchancer; in my opinion, it's useless garbage as a tool in ComfyUI, and text LLM work mostly works very slow in ComfyUI. There is no latent upscaling. Almost the same useless garbage. Maybe this is useful for T2V and that all. Basically the workflow is deprecated . I’m experimenting with LTX 2.5, mostly because things that don’t work in LTX 2.3 now work in LTX 2.5. LTX 2.5 is much faster, even at native 1080p resolution (with or without latent upscaling), the results look poor—details are bad. LTX 2.3, with boosted LoRas, isn’t very fast but

<iframe src="https://silytics.si/embed/item/0d0d0baf-4e84-45b1-bc82-376a40424268" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.