<h1 id="qwen-image-edit-low-resolution-input-repair-lora">Qwen-Image-Edit Low-Resolution Input Repair LoRA</h1><h2 id="model-introduction">Model Introduction</h2><a target="_blank" rel="ugc" href="https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit">Qwen-Image-Edit</a> is a powerful open-source image editing model. However, when the input resolution of the model is lower than the target resolution for image generation, the model's ability to maintain image details is poor. To address this, we made the following two modifications:<ol><li>Rope Interpolation: The position encoding of the input image in Qwen-Image DiT is changed to an interpolated sampling of the position encoding at the target resolution. This modification can take effect independently of modification 2.</li><li>LoRA Fine-tuning: Quickly train a LoRA model to enhance the generalization of this interpolated encoding by DiT.</li></ol>With these two modifications, the model can produce consistent edited images even when given low-resolution input. Additionally, compared to high-resolution input, the inference time of the model is significantly reduced. Source: <a target="_blank" rel="ugc" href="https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix">https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix</a>

Qwen-Image-Edit Lowres-Fix (Input Image Repair)

Qwen-Image-Edit Low-Resolution Input Repair LoRAModel Introduction<a target="_blank" rel="ugc" href="https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit">Qwen-Image-Edit</a> is a powerful open-source image editing model. However, when the input resolution of the model is lower than the target resolution for image generation, the model's ability to maintain image details is poor. To address this, we made the following two modifications:<ol><li>Rope Interpolation: The position encoding of the input image in Qwen-Image DiT is changed to an interpolated sampling of the position encoding at the target resolution. This modification can take effect independently of modification 2.</li><li>LoRA Fine-tuning: Quickly train a LoRA model to enhance the generalization of this interpolated encoding by DiT.</li></ol>With these two modifications, the model can produce consistent edited images even when given low-resolution input. Additionally, compared to high-resolution input, the inference time of the model is significantly reduced. <a target="_blank" rel="ugc" href="https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix">https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix</a>

Files with SHA256: 1d5e579c975d4810cca93bfe7ebe59c4adff23ddd8397b052d3f82f263fcdd76