Skip to content

Workflows Premium Workflows Templates Guides Work with us

LTX 2.3 text and image to video

Generate a video from text or a starting image, with a latent-upscaling stage.

LTX 2.3Video

LTX 2.3 · text-to-video · image-to-video · upscale · audio · ComfyUI

Workflow preview

LTX 2.3 text and image to video workflow overview showing node groups and connections

94 KB · JSON file

Need a hand? Load your workflow or troubleshoot your Runpod setup.

Replace prompt placeholders and supply your own input images, video or audio before running.

Models to download

Check the required model files before running this workflow.

gemma_3_12B_it_fp4_mixed.safetensors (ComfyUI/models/text_encoders)Model source for gemma_3_12B_it_fp4_mixed.safetensors (ComfyUI/models/text_encoders)
ltx-2.3-22b-dev-fp8.safetensors (ComfyUI/models/checkpoints)Model source for ltx-2.3-22b-dev-fp8.safetensors (ComfyUI/models/checkpoints)
ltx-2.3-22b-distilled-lora-384-1.1.safetensors (ComfyUI/models/loras)Model source for ltx-2.3-22b-distilled-lora-384-1.1.safetensors (ComfyUI/models/loras)
ltx-2.3-spatial-upscaler-x2-1.1.safetensors (ComfyUI/models/latent_upscale_models)Model source for ltx-2.3-spatial-upscaler-x2-1.1.safetensors (ComfyUI/models/latent_upscale_models)