This workflow takes an Image and an audio track as input to generate a video.
Important Notice
Update ComfyUI and KJ Nodes. A lot of the code has been updated in the last few days.
Include --reserve-vram 1 in your launch option to avoid OOM.
If you have no lipsync, try ensuring that your audio track is in stereo format. fix suggested by @thomasdimitri563
Models to download (LTX2.3)
Place in models/diffusion_models
Place in models/loras
https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-22b-distilled-lora-384.safetensors
Place in models/text_encoders
Place in models/vae
https://huggingface.co/Kijai/LTX2.3_comfy/blob/main/vae/LTX23_audio_vae_bf16.safetensors
https://huggingface.co/Kijai/LTX2.3_comfy/blob/main/vae/LTX23_video_vae_bf16.safetensors
Models to download (V3)
Place in models/diffusion_models
https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-fp8.safetensors
Place in models/text_encoders
Place in models/loras
Description
Changed to FP8 distilled model.
Set resolution at 1920 x 1088.
Changed to Manual Sigmas.
Changed to Native Video Save, to prevent saving 3 different files for final video.
FAQ
Comments (10)
What do? image I uploaded is 820x1093. Changed width and height to that in resize image node.
3090 and 64gb ram. I don't have other programs running, just 8 more tabs.
What do?
Try --reserve-vram 1 launch option.
제 유튜브 채널에 이 워크플로우를 분해해서 설명하는 영상을 올려도될까요? 너무 좋은 워크플로우라 LTX2를 욕하는사람들이 많은데 꼭 소개해주고싶어서요!! 물론 출처랑 제작자분 닉네임까지 같이 소개할꺼에요!!
워크플로가 잘 작동했다니 다행입니다. 영상을 올려주셔도 괜찮습니다. 출처를 밝혀주시면 감사하겠습니다. 한국어 번역이 정확하지 않더라도 양해 부탁드립니다. 구글 번역기를 사용했습니다.
I like the workflow but i would like to use this with the undistilled fp8 or fp4 version but I dont think the manual sigmas work. How can make this work? If I use undistilled it starts to ghost a lot.
follow what was done in this workflow: https://civitai.com/models/2337141/ltx-2-pose-image-audio-to-video
for the dev model, include negative prompt, increase the CFG to 3.5 - 4.0, and use the LTXVScheduler node (native comfyui).
Hello everybody! error message: SaveVideo
ndarray is not C-contiguous
What am I doing wrong?
I had the same issue but I fixed it. It's problem with your audio file. folllow this step to change it. by using Audacity, and it will work. Convert to Mono
Tracks → Mix → Mix Stereo down to MonoSet Sample Rate
Tracks → Resample → 48000 HzExport
File → Export → WAV@overnom I found a solution. I replaced the Save Video node with a VHS Video Combine. Now I have a video with good stereo sound.