LTX 2.3 Dual Character V2 is Here — Bigger, Faster, With Audio in ComfyUI

In this video, I'll show you the upgraded V2 workflow for cinematic two-character dialogue scenes using LTX 2.3 and the IC-LoRA Dual Characters inside ComfyUI. This is a major step up from V1 — now featuring audio-video generation, modular SetNode/GetNode, and Image to video, Text to video, custom audio. If you've been using the V1 workflow, this is the upgrade you've been waiting for.

Featuring IC-LoRA Dual Characterscivitai.com

Workflow

drive.google.com/file/ddrive.google.com

Model links

Models (dev)

BF16huggingface.co FP8huggingface.co GGUFhuggingface.co

Models (distilled)

BF16huggingface.co FP8huggingface.co GGUFhuggingface.co

models/text_encoders

gemma_3_12B_it.safetensorshuggingface.co ltx-2.3_text_projection_bf16.safetensorshuggingface.co

models/vae

LTX23_video_vae_bf16.safetensorshuggingface.co LTX23_audio_vae_bf16.safetensorshuggingface.co

models/loras

ltx-2.3-22b-distilled-lora-384-1.1.safetensorshuggingface.co Ltx2.3-Licon-VBVR-I2V-390K-R32.safetensorshuggingface.co

models/latent_upscale_models

ltx-2.3-spatial-upscaler-x2-1.1.safetensorshuggingface.co

Vocals Extraction

MelBandRoformer_fp32.safetensorshuggingface.co

• 👍 Support the Channel If you found this helpful:

• 👍 Like the video
• 🔔 Subscribe for more AI workflows
• 💬 Comment what you want to see next

#LTX23#ComfyUI#AIVideo#GenerativeAI#AIAnimation#DualCharacter#ICLoRA#AudioVideo