Here are some experiments with loras and ic loras that I trained. R2V Inpainting Workflow - <a target="_blank" rel="ugc" href="https://huggingface.co/Alissonerdx/LTX-LoRAs/resolve/main/ltx23_inpaint_masked_r2v_rank32_v1_3000steps.safetensors">https://huggingface.co/Alissonerdx/LTX-LoRAs/resolve/main/ltx23_inpaint_masked_r2v_rank32_v1_3000steps.safetensors</a> T2V Inpainting Workflow - <a target="_blank" rel="ugc" href="https://huggingface.co/Alissonerdx/LTX-LoRAs/resolve/main/workflows/ltx23_inpaint_v1.json">https://huggingface.co/Alissonerdx/LTX-LoRAs/resolve/main/workflows/ltx23_inpaint_v1.json</a>

LTX LoRAs

This is a IC LoRa ; to work, you need to add the video guide, which must contain the mask over the region you want to change. It won't be used with a separate mask; the mask needs to be over the video region. Workflow: <a target="_blank" rel="ugc" href="https://huggingface.co/Alissonerdx/LTX-LoRAs/blob/main/workflows/ltx23_inpaint_v1.json">workflows/ltx23_inpaint_v1.json · Alissonerdx/LTX-LoRAs at main</a>

Files with SHA256: 1f2089f5cd3cac56f93d3641c90695a7296514aa1292ec8c6f3a6ad369eda728