This Lora is used to generate cricketing shots - four types of shots can be produced - drive, pull, legglance, sweep ....Training Images used from the dataset used - <a target="_blank" rel="ugc" href="https://www.kaggle.com/datasets/aneesh10/cricket-shot-dataset">https://www.kaggle.com/datasets/aneesh10/cricket-shot-dataset</a>prompt : in a cricket match, a batsman wearing &lt;insert color&gt; uniform plays a &lt;insert shot type&gt;, in a large stadium, &lt;lora:cricket_shots:1&gt; negative:baseball, deformed body, bad quality, malformed face, extra limbsshot types are - drive, pull, legglance, sweepit generally tends to generate cover drive, but sometimes can give straight drive alsoUse baseball in negative prompt as it confuses cricket and baseball. It gives better results with 1024*1024 resolutionThe faces are distorted , but using an Adetailer gives reasonable facesI have tried using it with Juggernaut model but I guess it works with any major sdxl checkpoint.

Files with SHA256: 6f48f6220f814d0275dd4ff4f07faaf2707f51dc4ffbdb109df848c256c544a3