<h1 id="krea2-gptimage-stylelora">Krea2 GPTImage StyleLoRA</h1><p>A Krea2 style LoRA trained on 300 images generated with GPT-Image-2.5.</p><p>The training images were created using prompts derived from my own past and recent works, which were then used to generate new images with GPT-Image-2.5.</p><p>The uploaded images and their corresponding prompts are provided as references to give an idea of the visual direction and characteristics represented in this LoRA.</p><p>The actual results may vary depending on the prompts and generation settings used.</p><h3 id="trigger-word">Trigger Word</h3><p><code>GPTImage</code></p><p>Optional. The LoRA works without it, but using it makes prompt adherence more stable.</p><p>Because the captions are based on my own prompts, this LoRA may respond best to prompts written in a similar style.</p><h3 id="recommended-strength">Recommended Strength</h3><p>1.0</p><h3 id="generation-settings">Generation Settings</h3><p>Samplers used: <code>euler</code></p><p>Scheduler: <code>simple</code></p><h3 id="training">Training</h3><p>* Images: 300</p><p>* Network Rank: 64</p><p>* Training Steps: 3,000</p><p></p>

Krea2_GPTImage_StyleLoRA

<p>Initial release of Krea2 GPTImage StyleLoRA.</p><p>Trained on 300 images generated with GPT-Image-2.5, using prompts developed from my previous and recent works.</p><p>Recommended strength: 1.0.</p><p>Results may vary depending on prompts and generation settings.</p>

Files with SHA256: aa616410de6ce17c1be915128cc1e9d60e6a4bf346fbb757f76dfd6c80ee9361