LTX 2.5 text to video
Generate video and audio from a scene prompt with LTX 2.5 and latent upscaling.
All workflows
Workflow preview
91 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.
- These model files require Hugging Face sign-in and acceptance of the publisher's access terms before downloading.
Models to download
Check the required model files before running this workflow.
- gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors (ComfyUI/models/text_encoders)Model source (access required) for gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors (ComfyUI/models/text_encoders)
- ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors (ComfyUI/models/diffusion_models)Model source (access required) for ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors (ComfyUI/models/diffusion_models)
- ltx-2.5-audio-vae-bf16.safetensors (ComfyUI/models/vae)Model source (access required) for ltx-2.5-audio-vae-bf16.safetensors (ComfyUI/models/vae)
- ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors (ComfyUI/models/latent_upscale_models)Model source (access required) for ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors (ComfyUI/models/latent_upscale_models)
- ltx-2.5-video-vae-bf16.safetensors (ComfyUI/models/vae)Model source (access required) for ltx-2.5-video-vae-bf16.safetensors (ComfyUI/models/vae)