<h1 id="brazilian-male-realism-lora-v2-(z-image-turbo)">Brazilian Male Realism LoRA V2 (Z Image Turbo)</h1>⚠️ Check the Hugging face for more info, comparisons and prompt examples: <a target="_blank" rel="ugc" href="https://huggingface.co/olob0/z-image-turbo-brazillian-male-realism-lora-v2">https://huggingface.co/olob0/z-image-turbo-brazillian-male-realism-lora-v2</a>This is my second attempt to train a LoRA for Z Image Turbo, fixing some of the issues I had with the first one. This one is focused on improving the realism of Brazilian/Latin American pics, keeping the same quality of the base model.The goal is to reduce the the "realistic AI look"/"cozy-perfect" of the highly realistic images generated by Z Image Turbo, resulting in more natural proportions and imperfections, typical of real people, without exaggeration. In other words, it attempts to reduce the super-detailed, perfect appearance, making the images more similar to those taken with a cell phone.Trained with 100+ customized images of Brazilian men, with much more variations in skin tone and age compared to the V1. It was trained with more AI-generated images, using <code>ChatGPT-Image-2.0</code> for generations and <code>Google Nano Banana 2</code> for upscaling some images in the original dataset.<h2 id="usage">Usage</h2>- Recommended LoRA strength: It varies according to your preference. The closer to 0.5, the more similar the result is to the base model. The closer to 1.0, the more LoRA will interfere with the generation. Some images may work better with low intensity, and others with high intensity. Do your tests! Try something between 0.6 and 0.8 (~0.75).- Guidance: (CFG Scale): It is the same as the base model, <code>1.0</code>.- Steps: 8-10. It is the same as the base model, <code>8</code>.- Triggerword: <code>BRZMLRELSM</code><h2 id="limitations">Limitations</h2>- Sometimes, it can distort/corrupt text in images, especially small text.- For some reason, certain internal patterns, such as interior walls made of large blocks, may become slightly distorted if there isn't a specific description of them in the prompt. In other words, always describe what the background of the image will look like.<h2 id="license">License</h2>This model is licensed under <code>CC-BY-4.0</code>.You are free to use, modify and distribute this LoRA, including for commercial purposes, as long as proper credit is given to the original author.<h2 id="examples">Examples</h2>Check the Hugging face for more info, comparisons and prompt exemples: <a target="_blank" rel="ugc" href="https://huggingface.co/olob0/z-image-turbo-brazillian-male-realism-lora-v1">https://huggingface.co/olob0/z-image-turbo-brazillian-male-realism-lora-v2</a>

Files with SHA256: 907ce17dffe11c87c8d29b3bbd45b1098b305f72e5ea876666d5838f23b86871