https://civitai.com/models/1767712/fabled-infusion-il-xl-nsfw?modelVersionId=2136344
(Semi & photo realism, with an eye to the artful).v1 -(best for simi-realism, creative composition)v2 -(best for full photorealism, detailed skin texture)These models can use both Illustrious and XL Loras, though you may need to adjust the weights a bit.Please Rate! - Your feedback, ratings or a follow are greatly appreciated. - Thankyou!I used a face detailer in about 10 of the 20 example images, and most use upscaling (4x-nickelback). A face detailer is generally helpful depending on zoom level, If your subjects face is about 30% or more of the image it can be detrimental. I urge experimentation in all areas.V2 - Fully REALized - (greater photorealism while maintaining much of the illustrious knowledge base)Suggested settings:VAE: sdxl_vae (baked in)Clip skip: 2 was used during merge, (setting 1 or 2 should yield same results)Sampler: DPM++ 2M SDE - SGM Uniform, (good option for photorealism) or Euler Ancestral - SGM Uniform (experimentation is recommended),Resolution: all standard 1MP resolutions work well in portrait and landscape, (depending on context) (I often use 1024x1360 and 1120x1440 in portrait and landscape)CFG: 2.8 - 9.0 (I commonly use 3.8, 5 & 7)Steps: 30 - 40 (I use 36 most often)V1 - Beyond the ValleySuggested settings:VAE: sdxl_vae (baked in)Clip skip: 2 was used during merge, (setting 1 or 2 should yield same results)Sampler: Euler Ancestral - SGM Uniform (most consistent good results), DPM++ 2M SDE - SGM Uniform, (good option for photorealism)Resolution: all standard 1MP resolutions work well in portrait and landscape, (depending on context) (I often use 1024x1360 and 1120x1440 in portrait and landscape)CFG: 2.8 - 8.0 (lower for more photorealism - I commonly use 2.8, 3.8, 5 & 7)Steps: 30 - 40 (I use 36 most often)Prompting:Primarily Danbooru tags, mixed with a bit of natural language prompting. Generally less is more, for best results try to write clear concise prompts, (look to my sample images for examples and general formatting).positive prompts - Hype4realistic can be added to push realism a bit further.negative prompts - I generally recommend starting with none and adding tags as needed. (it can be helpful to add a few things like "toon, illustration, unreal", if you're pushing for greater realism).I started this project to in an attempt to recreated a specific aesthetic created by blinkdotleh using his workflow where 2 models split the steps during image generation. He created a series of images using Uncanny valley for the initial steps & my fabled Illusion model as a refiner. I created a style Lora from those outputs and included it in this merge. This is an attempt to recreate that look in a singe model while preserving as much of the Illustrious knowledge base as possible.on the image generation side, this is roughly 50% Illustrious & 50% XL (mostly bigASP), while the CLIP more heavily favors Illustrious at about 65%.Resources used / Creator thanksCheckpoints:iLustMix by GZeesBigASP v2.0 by nutbutterUncanny valley by meden - (clip only)IterComp by AdvokatFabled Illusion by ME :) (prodajie)Loras:Hyperrealistic [Pony | Illustrious] by ZoropatonSPO-SDXL_4k-p_10ep_LoRA_webui by rockeycosscustom style Lora - (not yet publicly available)(Additionally, thanks to everyone whos prompts I've pilfered for testing).
