Image-to-Video
LTX-2
lora
ic-lora
ltx-video
ltx-2.3
video
video-to-video
3d-to-real
render-to-real
photorealistic
cgi
fal
Instructions to use fal/LTX-2.3-3DREAL-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX-2
How to use fal/LTX-2.3-3DREAL-LoRA with LTX-2:
# 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 fal/LTX-2.3-3DREAL-LoRA --local-dir models/LTX-2.3-3DREAL-LoRA hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Video-to-video with the IC-LoRA (runs on the distilled base model) uv run python -m ltx_pipelines.ic_lora \ --distilled-checkpoint-path path/to/distilled_checkpoint.safetensors \ --spatial-upsampler-path path/to/spatial_upsampler.safetensors \ --gemma-root models/gemma-3-12b \ --lora models/LTX-2.3-3DREAL-LoRA/<weights>.safetensors 1.0 \ --video-conditioning reference.mp4 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 - Notebooks
- Google Colab
- Kaggle
LTX 2.3 Comfyui workflow?
#1
by pduncan - opened
Can you share the comfyui workflow to use the lora?
Is it possible to run this on comfyui ?
i create this one: https://github.com/peterducan-hub/PeterDuncan_Comfyui/blob/main/Ltx%202.3_IC_LORA_3DReal.json
Hi! I'm pretty noob yet on my learning way. Have run through your workflow (big thanks for sharing!). Curious to know, if have you reached any result?
And would be grateful if you may give a hint on my problem - I tried to proccess 3s long guide video (73 frames with 24fps), but as output get a 6s for first pass and 9s for upscale pass with weird visuals (like it's a first sampling step). Really can't figure out the reason and point to fix. Thanks in advance!