Instructions to use RuneXX/LTX-2.3-2.5-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use RuneXX/LTX-2.3-2.5-Workflows with LTX.io:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download RuneXX/LTX-2.3-2.5-Workflows --local-dir models/LTX-2.3-2.5-Workflows hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/LTX-2.3-2.5-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3-2.5-Workflows/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/LTX-2.3-2.5-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3-2.5-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3-2.5-Workflows/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
LTX-2.3_-_V2V_Just_Talk_add_lipsynced-voice_to_any_video - With Custom Audio File
Hi RuneXX,
I am trying to create videos of talking animals - cats, dogs, turtles, goldfish, etc. I think your workflow is great for this, but it seems to be missing an option to insert a custom audio file that matches the video length. I’ve tried to figure it out but haven't had any luck. Can you help? Also, one question - will the output video be identical to the original, just with the added lip-sync motion if there was a custom audio option? Thank you :)
This particular workflow you just prompt the dialog/voices.
It could be added a custom audio input though, i'll add an optional one.
But there are already custom audio workflows you could use. Or even the Qwen / Fish Audio ones that is sort of a combo of both. You upload an audio clip to clone, and then prompt what to say based on the sound of that input voice.
Thank you RuneXX.
A custom audio input file to control the lip-sync animation will definitely be a game-changer for me. Do you have a donation link?
Thats all the donation i need ;-) hearing people having fun with it ..
And happy to hear you are
I might add, I am interested in something like this too. I have a nice way to generate voices, would love to see if I could get it to animate to that voice. V2V_Dub_It_Lip-synced_dubbing_multilanguage has done a lot for me, just would be nice if the audio I have is too slow for what LTX generates then it doesn't match anymore.
I might add, I am interested in something like this too. I have a nice way to generate voices
You have your own custom audio you mean?
You could try the I2V custom audio workflows then. Or do you mean with a V2V workflow?
I might add, I am interested in something like this too. I have a nice way to generate voices
You have your own custom audio you mean?
You could try the I2V custom audio workflows then. Or do you mean with a V2V workflow?
Yes I have my own custom audio... V2V workflow would work best, but I should look at the I2V custom audio workflows too, I want to see if I can "lip-sync" an already existing video with audio I have... but I don't know if that is possible with LTX yet. I also just noticed some other new workflows you made that I want to try and play around with.
, I want to see if I can "lip-sync" an already existing video with audio I have... but I don't know if that is possible with LTX yet
Should be possible, but a little limited since the way would be to mask the mouth area (or face for more motion).
Will add a custom audio to the lip sync workflow.
Alternatively take the first frame of your video and let LTX be more creative, and re-do a video based on that frame, your audio and prompt