This was a labor of love. This is my first LoRA and was a great learning experience.Trained on 113 manually captioned images with an average resolution of 3500x3500.The majority of this dataset is in a portrait orientation; over half of the images have an aspect ratio between 1.5 and 1.75, so you will get the best results by adhering relatively closely to this ratio. Roughly 1/4 of the set is between 0.67 - 0.8, so it can handle wider ratios, though they may be somewhat unstable. Most example images use 832x1216, though it can easily generate at 1536x1536 thanks to the high resolution of the training set.Changelog:V1.7 Illustrious - Retrained from the ground up. Higher resolution images, a pruned dataset, manually removed all signatures and watermarks, and manually recaptioned the entire thing following the Illustrious team's own tagging methodology. Trained using a different optimizer and the results seem much better. Better detail, more painterly aesthetic and better prompt adherence. Use 1eq2 at the end of the prompt for best results. Add "painterly" for more brushstrokes. Noob 1.7 coming soon.V1.6 NoobAI: Once again, better in every way compared to 1.5. Add "realistic" ("intricate detail" optional) for a more painterly effect. Euler for rougher/painterly effect, Euler A for a more typical anime effect, DPM++ 2m for a middle ground. Weight 1 works fine, may drop to 0.8 for more detailed/complex prompts if anatomy gets weird.V1.6 Illustrious: Significantly improved colors, style and prompt adherence. Generic, open-ended prompts will show the base style more heavily - prompt "1girl, solo" and you'll see what I mean. Guiding the prompt will lessen this. I recommend using "Realistic" and possibly "intricately detailed" for best results. V1.5 Noob: You asked, I listened! See the model changelog for details. Please leave feedback - I'm curious to see how it works with merges and finetunes. V1.5: Better than V1 in pretty much every way. I tested primarily with PrefectIllustriousXL V1.0 and WaiNSFWBranchRouWei_epred1 and it works great on both. You may benefit from adding "realistic" to your prompts with either model, particularly WAI as sometimes the base anime theme can overpower the lora. This version may be slightly overfitted, so dropping down to 0.8 can help in some cases.Does well:<ul><li>General character features and poses</li><li>Outfits, accessories and materials (see below for recommended keywords)</li><li>Facial expressions</li><li>Fluids</li><li>General piercings</li></ul>Is capable of / generally does well:<ul><li>Fetish gear</li><li>BDSM-specific poses and equipment</li><li>Yuri</li><li>Penetration (use femdom for more consistency)</li><li>Hands (using hiresfix solves this for me in most cases - not tested with adetailer)</li></ul>RECOMMENDED TAGS (pick and choose, don't use them all):Concepts: bdsm, bound, bondage, yuri, femdom, saliva, drooling, gagged, frogtie, hogtieClothing and Accessories: latex, ballerina, nurse, maid, nun, fake animal ears, oxygen mask (use with "tube"), respirator, toeless legwear, stirrup legwear, frills, hair ornament, hair flower, detached collar, bobby socksBDSM Gear: ball gag, bit gag, spider gag, harness, stationary restraints, anal tail, speculum, ballet boots, spreader bar, nose hook, linked piercing, blindfold, shibariNEGATIVES:All the normal no-nos from Civitai generation. Use common sense and be responsible.RECOMMENDED PARAMETERSLora Strength: Works great at 1, but dropping to 0.8 can help if it's struggling with anatomy in certain posesDimensions: 832x1216, 768x1344, 800x1296, 1024x1536, etc.For landscapes, just reverse the resolutions.Samplers: Euler, DPM++ 2M, DPM++ 2M SDEUPSCALINGResize Scale: 1.5Refine Sampler: Generating with Euler and then selecting DPM++ 2M SDE here allows for a nice blend of creativity and added detail. Otherwise, same as primary.Strength: 0.3 if you're happy with the current level of detail, otherwise 0.35.Steps: Roughly half of your primary steps.

1equals2 for NAI/Illustrious

Rebuilt from scratch - sourced higher resolution versions of many images and manually captioned every image following the Illustrious team's tagging schema from their whitepaper. All watermarks and signatures manually removed. Retrained using a different optimizer. Added a style token - add 1eq2 as the last token in your prompt. Add "painterly" for more brushstrokes (more faithful to the style.) This version works best with models that trend towards more western styles, or that are not trained with an anime bias. LunarGrapeMix (besides being a fantastic model in general) works exceptionally well with this lora and is highly recommended.

Files with SHA256: cec8fa7b665af6895726fff3e4d445ed5d15fe67e933511df05f5b49abc807cd