This one definitely my favorite so far and in my opinion, my best work. The quality turned out quite amazing on this one. Not to mention being quite flexible while retaining quality. For my next model I'm trying quite a larger dataset of training images to see if it improves quality even further. My assumption is that there's diminishing returns.8000 steps. Trained in local Kohya install. 4090. Trained on DreamShaper XL1.0 Alpha2. I followed <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=AY6DMBCIZ3A">SECourses SDXL LoRA Guide</a>.Most images were on DreamShaper XL A2 in A1111/ComfyUI. Hi-res fix with R-ESRGAN (1.25) and 0.2-0.4 denoising strength. Upscaled using "4x_NickelbackFS_72000_G" or "4x_NMKD-Siax_200k"Help me out by liking and following me to see my new models. Submit some of your outputs and post your SUGGESTIONS in the comments below. I am pacing around 6-10 models weekly depending on my actual job workload. If you liked my models and want to support the work I do you can buy me a <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/AIENGI">pizza! </a><a target="_blank" rel="ugc" href="https://github.com/AIENGI/AIENGI/tree/main">List</a> of upcoming LoRAs I intend to do as well as what I am currently working on.

Files with SHA256: 55e1be6996d3694173d14a140e492c1d3f7e3ba589659b7a50a71a826b200efa