<h1 id="slingshot-swimsuit-026xmc0ky">Slingshot Swimsuit</h1><h3 id="description-ogm5qgfd8">description</h3><ul><li>First Flux LoRA</li><li>all of sample image made it Flux.1 Dev GGUF Q4</li><li>recommended weight : 0.75 - 0.8</li></ul><h3 id="trigger-word-utmy2x9h0">Trigger Word</h3><ul><li>[color] slingshot swimsuit</li></ul><h3 id="training-details-y8ln164le">Training Details</h3>Dataset<ul><li>black slingshot swimsuit 17 images</li><li>blue slingshot swimsuit 15 images</li><li>green slingshot swimsuit 18 images</li><li>orange slingshot swimsuit 16 images</li><li>pink slingshot swimsuit 17 images</li><li>purple slingshot swimsuit 10 images</li><li>white slingshot swimsuit 10 images</li></ul>parameters<ul><li>resolution = 1024</li><li>batch size = 1</li><li>dim,alpha = 32,32</li><li>mix/save precision = bf16/bf16</li><li>optmizer = AdamW</li><li>UNet LR = 1e-4</li><li>TE LR = 5e-5</li><li>scheduler = cosine_with_min_lr (min_lr_ratio 0.67)</li><li>l2 loss</li></ul>steps<ul><li>epochs = 10</li><li>total steps = 2560</li><li>repeats = 2,2,2,2,2,3,3</li></ul>tools<ul><li>kohya-ss GUI v24.3.0 (Forked by me)</li><li>torch 2.5.0 cu124</li><li>Runpod RTX 4090 24 GB + xformers + gradient_checkpointing</li></ul>weight<ul><li>UNet average weights : 0.004571231384353156</li><li>TE1 average weights : 0.007479375422311326</li></ul>*This LoRA is for studying LoRA training with Flux*REPOST model is not allow if you found this model please report to me.

Files with SHA256: 75dec229dcfb4bbac8952135e00389f02ab0476fcb5126fd448d96d85f865853