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 LoRA can be used in two ways:<ul><li>Reference-guided inpainting, where the reference image actively guides the replacement</li><li>Text-only style inpainting, by sending a blank image as the reference input</li></ul>See more details at <a target="_blank" rel="ugc" href="https://huggingface.co/Alissonerdx/LTX-LoRAs">https://huggingface.co/Alissonerdx/LTX-LoRAs</a>

Files with SHA256: 0da59538eaa5737ad030e1459c9b22505696add818a413322cd04911798d220a