LTX Video 2.3 version 1.1 GGUF Image to Video

Use this ComfyUI image-to-video workflow to turn an image and a prompt into two videos: one with audio and one without. It is a GGUF workflow for LTX Video 2.3 version 1.1.

The nodes are wired and visible in grouped sections, with no set/get nodes or subgraph.

Drag an image into the image nodes, adjust the prompt, and press queue.

Sugerencia · sin verificar

The outputs are two videos: one includes audio and the other does not.

Use it in ComfyUI with the LTXV 2.3 base model.

The workflow was generated with 32 GB of VRAM and includes a ram saver node that you can enable.

Listed model files include: gemma_3_12B_it_fp8_scaled.safetensors, ltx-2-19b-distilled-lora-384.safetensors, ltx-2-spatial-upscaler-x2-1.0.safetensors, ltx-2.3-22b-distilled-1.1-Q5_K_M.gguf, and ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors.

Additional listed model files are: ltx-2.3-spatial-upscaler-x2-1.1.safetensors, LTX23_audio_vae_bf16.safetensors, taeltx2_3.safetensors, LTX23_video_vae_bf16.safetensors, and ltx-2.3_text_projection_bf16.safetensors.

Listed node packs are: comfyui-custom-scripts, ComfyUI-GGUF, comfyui-kjnodes, comfyui-videohelpersuite, and rgthree-comfy.

If you need to try a lower-memory setup, enable the ram saver node before queueing.

Sugerencia · sin verificar

The example video uses 1024 × 576 resolution.

Before use, verify that every listed model file and node pack is available in your ComfyUI setup.

Sugerencia · sin verificar

VAE decoding is described as a bottleneck that froze the author's rig, and Linux use has not been tested.