My first pony compilation, as always I have attached great importance to quality!It's harder to create reasonably realistic images with bangs, but the rendering of limbs and face is much better than SD1.5!The model can of course also represent NFSW up to the extreme. I prefer the ability to create photoshoot-like results.I also often use very extensive prompts for bangs, with as few Lora's as possibleI will link my favorites here.Hey, I built a small tool called PromptCleaner – it removes brackets and weightings like <code>(word:1.2)</code> from AI prompts. Maybe it’s useful for someone. Works with things like Stable Diffusion, ComfyUI, and similar tools. 👉 <a target="_blank" rel="ugc" href="https://github.com/LordKa-Berlin/PromptCleaner">https://github.com/LordKa-Berlin/PromptCleaner</a>ATTENTIONfor all who want to recreate my work!I use the Dynamic Thresholding Extension for Stable Diffusion for almost all my work<a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding</a>This makes higher CFG values and steps possible!I can only recommend it to you!

Files with SHA256: 2d095763164e4c35fc6b95a9219048e7a5d1d66b05ec43737c2f28a23606af9c