<h2 id="v2-advanced-weighting-and-various-improvements">V2 - Advanced weighting and various improvements</h2>Highly recommend just using the new workflow (included .zip or in example workflows on the github)<hr /><h3 id="installation:">Installation:</h3><h3 id="you-need-diffsynth-studio-first:click-this-to-go-to-my-github-readme-for-installation-instructions-for-your-setup">You need DiffSynth-Studio FIRST: <a target="_blank" rel="ugc" href="https://github.com/by-ae/ae-in-workflow?tab=readme-ov-file#-installation">CLICK THIS TO GO TO MY GITHUB README FOR INSTALLATION INSTRUCTIONS FOR YOUR SETUP</a></h3>(But I already installed):Please go to the link above anyway and confirm THAT is how you installed.<hr /><h3 id="(optional)-before-starting:">(Optional) Before Starting:</h3>You can use the built in modelscope download to grab the files for you automatically though you can get them much faster manually with huggingface if you know what you are doing (and where to put them) Otherwise, just be patient, it only needs them once.<hr /><h3 id="https:github.comby-aeae-in-workflow"><a target="_blank" rel="ugc" href="https://github.com/by-ae/ae-in-workflow">https://github.com/by-ae/ae-in-workflow</a></h3>

Custom Nodes Z-Image I2L2I (Single Pass LoRA Create & Use) & Image Selector

<ul><li>Per-Image Weighting: Added lora_weights parameter for individual image contribution control</li></ul><ul><li>Smart Size Reduction: Implemented size reduction option with weight-similarity sorting for intelligent LoRA compression without losing too much quality (experimental) for tons of images in an i2L lora.</li></ul><ul><li>Strength Normalization: Added normalized_strength parameter for target LoRA intensity control</li></ul><ul><li>Size Compression: Added reduce_size_factor for configurable LoRA size reduction through batching</li></ul><ul><li>Custom Decoder: Subclassed ZImageUnit_Image2LoRADecode and added advanced merging logic</li></ul><ul><li>Slight Memory Optimization: Replaced tensor stacking with iterative accumulation to reduce VRAM usage</li></ul>

Files with SHA256: 25842083450fb173ec98fad312703af2056dc92a4f0efaca636198d0dea5429f