This workflow takes an Image and an audio track as input to generate a video.

Important Notice

Update ComfyUI, KJ Nodes and ComfyUI-GGUF. A lot of the code has been updated in the last few days.

V2 update

Changed to use the native comfyui loaders. The KJ loaders seem to be giving noise for some generations. We are using the official LTX-2 release for the VAE and Kijai's release for diffusion model GGUF. Changed to allow loading of an audio file for input.

Models to download

Place in models/diffusion_models

https://huggingface.co/Kijai/MelBandRoFormer_comfy/resolve/main/MelBandRoformer_fp32.safetensors?download=true

https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/diffusion_models/ltx-2-19b-distilled_Q8_0.gguf?download=true

https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-dev-fp8.safetensors

Place in models/vae

https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/VAE/LTX2_video_vae_bf16.safetensors?download=true

https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/VAE/LTX2_audio_vae_bf16.safetensors?download=true

Place in models/text_encoders

https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/resolve/main/gemma_3_12B_it_fp8_e4m3fn.safetensors?download=true

(not needed in v2 of the workflow) https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/text_encoders/ltx-2-19b-embeddings_connector_distill_bf16.safetensors?download=true

Place in models/loras

https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/resolve/main/ltx-2-19b-ic-lora-detailer.safetensors?download=true