Due to the new site policy, in newly published models, there will be only 2-5 pictures, as an example. so as not to "offend" anyone.There was something without brains that creates, constantly, new accounts, and put one star in the reviews. of course, without any arguments. not because the model is bad, but because he is an idiot, and he tries to prove it with all his actions.Singerthe training was on a model - CyberRealistic 3.1 in resolution 768x768, and used a dataset of 44 images.I'm Render on - EndlessReality (I like the result of rendering from this model the most)<ul><li>if you want to get speed, drive a sports car</li><li>if you want to drive off-road, take an SUV</li><li>if you want to hammer a nail, take a hammer</li><li>it's the same here - if you want to get results, read the recommendations and follow them</li></ul><h3 id="i-do-not-recommend-using-my-lora-with-model-realisticvision">I do not recommend using my LoRA with model RealisticVision</h3>personally, I most often perform generation with parameters: DPM ++ 2M Karras, Sampling Steps 36, Denoising strength 0.35, CFG Scale 3.5-8.5the weight of the model is approximately 0.75-0.85

Files with SHA256: 91d70f5fa7921fd15fc0ece33667aa6b72d304f44a28acb99892a0489afe637b