DISCLAIMER: This is my first attempt at training for Stable Diffusion. Despite all the time and effort put into it, I consider this version of ScytheXL, v0.24.224.05, a prototype. So you may encounter some odd results and/or other bugs during use, ones I will do everything I can to resolve for future versions of ScytheXL. That said, thank you in advance for all for your patience, as well as for any help/improvements you may be able to provide!TIPS: <a rel="ugc" href="https://ko-fi.com/domiluci">Ko-Fi</a>QUICK DETAILS:<ul><li>ScytheXL is a simple SDXL LoRA made to generate scythes and characters holding scythes using Stable Diffusion's SDXL 1.0 models.</li><li>This LoRA was trained on SDXL 1.0 Base, and then two versions with different desired strengths/weaknesses were merged into each other to stabilize the resulting output.</li><li>As such, this LoRA seems to work on most realistic models of base SDXL 1.0 heritage I've tried. But unrealistic SDXL 1.0 models produce some results that are... interesting.</li><li>I trained this LoRA on the base SDXL VAE, so I've been using that during testing. Although I prefer <a target="_blank" rel="ugc" href="https://civarchive.com/models/455138/sharpspectrumvaexl">Sharp Spectrum</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/199948?modelVersionId=224985">Flatpiece</a> VAEs over the base SDXL VAE.</li><li>It is imperative that you use the trigger word or phrase if you want this LoRA to work, these being "scyth3" and "holding a scyth3". Very important!</li><li>The strength settings I used varied by model but, typically, sat between 0.65 to 0.85. Usually 0.7 or 0.75 works perfectly. But I varied this more for unrealistic models.</li><li>I went through pretty much every sampler available in Forge during testing. This LoRA performed reasonably well all around. So my sampler recommendation is "dealer's choice".</li><li>CFG isn't something I normally play with, so I've just been going between CFG 6 and CFG 7. Another "dealer's choice", if that's something you use.</li><li>Hires Fix and ADetailer were used with sample images. I used Foolhardy's <a target="_blank" rel="ugc" href="https://civarchive.com/models/147759/remacri">Remacri</a> at 2x with Denoise at 0.39 for HRFix, and then ADetailer on face and hands.</li></ul><h3 id="the-story:-no3f28sqd">THE STORY:</h3>This project started in June 2024 while working on another Stable Diffusion related project involving a character that was meant to wield a scythe. A plain, traditional, reaper-esque scythe. I started with some GPT-infused, next level prompt engineering, and then I tried looking for LoRA models and Embeddings meant to generate scythes, but none really existed. Eventually I came to the realization this just couldn't be done with the tools available. At least, not yet.With a group of 20 awful photos pulled from Google, I started training LoRAs with pretty terrible results, but just okay enough to develop a viable dataset with. After a lot of (re)training and grinding, I ended up with 100 unique, high quality images in total. With that new dataset, I started training variations of this ScytheXL LoRA, in an effort to find which combination produced the best LoRA, until I finally settled on the LoRA I've uploaded here.However, this LoRA model is more of a proof of concept or prototype than a beta, one that is very much in its infancy. Therefore, YMMV. But I do want to thank everyone, in advance, for all the support and patience they afford me and my model!I wish you all the very best and lots of AI fun!- <a target="_blank" rel="ugc" href="https://ko-fi.com/domiluci">Dom</a>

ScytheXL

This is v0.24.224.05, the inaugural version of ScytheXL!NOTE: This version is considered a prototype; it may be buggy and/or not produce desirable resultsQUICK NOTES:<ul><li>Triggers: "scyth3" and "holding a scythe"</li><li>Strength: 0.65 to 0.85, but optimal is 0.7 or 0.75</li><li>Sampler: This one is up to you</li><li>CFG: CFG 6(.5) to CFG 7, but CFG 7 seems better</li><li>HRFix: <a rel="ugc" href="https://civitai.com/models/147759/remacri">Foolhardy Remacri</a> at 2x; Denoise at 0.39</li><li>Trained for, but not limited to, realistic SDXL models</li><li>Triggers may work better in parentheses</li><li>Plain or simple BGs seem to improve generations</li><li>These are suggestions only. Experiment and have fun!</li></ul>As stated, this is my first attempt at training for Stable Diffusion, and this specific LoRA model is really more of a prototype than anything else. So this is all a wild learning experience that I hope will bring knowledge and enjoyment to us all, and hopefully help someone along the way. So thank you for your patronage, support, and patience!

Files with SHA256: 9c088221519a71d3918df445a066726e30b5687750a0b70b1860ee6241763b12