LTX 2.x inference with ComfyUI¶

Run LTX-2.x video and audio generation in ComfyUI on RunPod. The template provisions the models, text encoders, VAEs, LoRAs, custom nodes and example workflows needed for text-to-video, image-to-video and video-to-video generation.

What to expect¶

The template is intended for users who want to run ComfyUI on RunPod and are comfortable following technical setup steps. No Linux expertise is required for normal use, but basic familiarity with RunPod pods, logs, tokens and file management is helpful.

The pod is an experimental workspace for video creators who want to combine generation models, editing models, LoRAs and custom nodes in open and flexible creative pipelines. It supports video and audio generation, pose transfer, prompt enhancement and longer video workflows.

The approach is aligned with the open-model discussion in Eric Hartford's Uncensored Models: local and open AI systems give advanced users more ownership, control and composability. The pod is a technical workspace for responsible use rather than a content platform or safety policy.

Included features¶

Complete LTX-2.x model chain.
Public ungated LTX-2.5 model chain from comfyicu/LTX-2.5.
Community Heretic BF16 and INT8 ConvRot text-encoder profiles selected by GPU VRAM.
Video and audio VAEs, spatial and temporal latent upscalers, and a duration-head patch.
CUDA 12.8 with compiled attention and GPU acceleration.
ComfyUI, Code Server, SSH and LoRA Manager.
Authentication for Hugging Face and CivitAI.

RunPod deployment¶

Start here: Deploy and start the LTX template on RunPod.

Once the pod is running, use the workflow examples below to choose what you want to create. Follow the ComfyUI tutorial for the steps from opening ComfyUI to running your first workflow.

Choose a workflow¶

Goal	Input	Recommended workflow	Go to
Animate a still image	Image and prompt	LTX-2.5 image-to-video	Workflow
Generate a video from a description	Text prompt	LTX-2.5 text-to-video	Workflow
Transfer a pose from a source video	Source video and pose reference	LTX-2.3 DWPose transfer	Workflow
Transfer a pose while adjusting body proportions	Source video and pose reference	LTX-2.3 SDPose transfer	Workflow