Here I will share some LoRAs that I trained for LTX 2.3.
These LoRAs may cover different use cases over time, so this repository is not limited to inpainting only.
| File | Description |
|---|---|
ltx23_inpaint_rank128_v1_02500steps.safetensors | Sometimes this checkpoint follow the prompt better, probably because it experienced less overfitting. |
ltx23_inpaint_rank128_v1_10000steps.safetensors | Sometimes this checkpoint doesn't follow instructions quite right, because it focuses more on the size of the mask.; but other than that, it uses the masked region better. This is probably because it experienced more overfitting after a longer training period on a more limited dataset.. |
Use whatever suits you best.
These inpainting LoRAs were trained with a specific guide and mask setup, so input preparation during inference is important.
During inference, you should not pass the mask as a separate channel.
The mask must be embedded into the guide video, which means:
- the mask video
- and the guide video
must be treated as a single video.
After that, you need to use the LTXVAddGuideMulti node to pass the guide video into the model.
My dataset included samples where the mask was more blockified. In other words, the default pattern used 8x8 blocks.
To better reproduce the training conditions during inference, you can use:
Blockify Maskfrom KJNodes
This may help make the mask distribution closer to what the model saw during training.
- Base model:
Lightricks/LTX-2.3 - Checkpoint behavior may vary significantly in terms of:
- prompt adherence
- use of the masked area
- overfitting tendency
For the inpainting LoRAs in this repo:
- If you want better prompt adherence, try the 2500 steps checkpoint first
- If you want better use of the masked area, try the 10000 steps checkpoint first
The best approach is to compare both in your workflow, since preference may vary depending on the scene, mask, and prompt.
Model: ltx23_inpaint_rank128_v1_02500steps.safetensors
Video:
Prompt:
Model: ltx23_inpaint_rank128_v1_02500steps.safetensors
Video:
Prompt:
Model: ltx23_inpaint_rank128_v1_10000steps.safetensors
Video:
Prompt:
Model: ltx23_inpaint_rank128_v1_10000steps.safetensors
Video:
Prompt:
