Extend a video on any side, and LTX 2.3 paints the new area. Your video goes back on top of the result, and its sound is kept.
How to use it
Load your video.
Pick a ratio. It opens on 16:9, which turns a phone clip into a wide one. The small button next to the ratios flips portrait and landscape.
Press Run.
What you need
AusBoss nodes 2.3.0 or newer. In ComfyUI-Manager, search "AusBoss". Already have them? Update first.
The LTX 2.3 models and the two LoRAs:
ltx-2.3-22b-dev_transformer_only_fp8_scaled.safetensors →
models/diffusion_models· 23.5 GBgemma_3_12B_it_fp8_scaled.safetensors →
models/text_encoders· 13.2 GBltx-2.3_text_projection_bf16.safetensors →
models/text_encoders· 2.31 GBLTX23_video_vae_bf16.safetensors →
models/vae· 1.45 GBltx-2.3-22b-distilled-1.1_lora-dynamic_fro09_avg_rank_111_bf16.safetensors →
models/loras· 2.74 GBltx-2.3-22b-ic-lora-outpaint.safetensors →
models/loras· 1.31 GB
The sample clip is in
sample_inputs.zip. Put it inComfyUI/input, or load your own video.
Tips
Keep the fill color black. Pure black is what the IC-LoRA paints over. Gray or any other color comes back as a flat bar.
Crop out edges that confuse it. Noise, a frame line or a busy strip along the edge of your clip can make the new area come out strange. Drag the blue handles on Video Crop + Rotate + Pad inward to cut those edges off first.
It makes 97 frames from IN, about 4 seconds at 24 fps. Drag IN on the timeline to pick the start. On a 60 fps clip, set Every nth to 2 or 3 for more seconds.
Very dark footage can come back flat. Night or underwater clips can read as a bar. Brighten the clip first (gamma 2.0) and darken the result after (gamma 0.5).
Out of memory? Lower Megapixels on the video node, or use the smaller int8_convrot transformer in the same Kijai folder.
Part of the new area still black? Run it again with another seed.
About 2 minutes a run for a short clip on an RTX 5090, model loading included.
Credits
LTX-2.3 is by Lightricks, under the LTX-2 Community License: companies making US$10M or more a year need a paid license from Lightricks. The ComfyUI files are Kijai's split, and Gemma 3 12B is Google's model, packaged by Comfy-Org. The outpaint IC-LoRA is by oumoumad, under the same license. The sample clip was made with Qwen Image 2.1 and MiniMax H3, and their licenses cover it.
v1.1 (2026-09-30): a smaller workflow, and the new area gets painted on any clip. v1.0 (2026-09-25): first release.
Questions or bugs: GitHub issues or the comments here. More from me on X @Zanzibased and GitHub.
Description
The workflow is smaller: 13 nodes instead of 23, with the plumbing in two boxes.
The prompt instructions have their own Text node, Prompt instructions, instead of sitting inside Generate Text.
The video loader is saved empty, so ComfyUI no longer flags a missing file when the workflow opens.
Both LoRAs load in one LoRA Loader.
The outpaint LoRA runs at strength 1.5 instead of 1. At 1 it only just tipped LTX into painting, and the prompt, the seed or the canvas could tip it back: the new sides came back black.
New prompt instructions: Gemma now writes a wide shot and describes what surrounds the subject on every side, out to the edges. You no longer edit them when you add space at the sides, so that step is gone.
It opens on 16:9. A portrait phone clip, the most common use, comes out wide; a 9:16 clip into a 9:16 canvas has nothing to paint.
About 2 minutes for a short clip on an RTX 5090, model loading included.
The same models. Needs AusBoss nodes 2.3.0 or newer.
FAQ
Comments (2)
Excellent, works like a Charm, I use Comfy 0.34 & frontend 1.52.7 , & AusBoss nodes version 2.5.0 works well & the look & design of the nodes Ui is awesome.
Soon I am also trying the Flux Klein & LTX versions.
sweet! let me know if you have any issues or suggestions