PicXer by me. My first lora, so on.support me on Ko-fi / BoostyPicXer is an extract of PicX_real + a bit of magic. The magic will be different, so the effects will be different.Two types of PicXer are now available:PicXer_real: it's a realistic enhancer, but like PicX_real, it can be used for sci-fi, fantasy, with different styles and lora (also compatible with PicX_real)PicXer_bside (new!): it's a atmosphere enhancer that goes well with the aesthetic of dark shots, gloom, horror, fashion, and similar thingsPicXer_real can:1. Add realism in the style of PicX_real model (more details, better light, texture, hair, more knowledge about various effects and entities, etc.) - see the grid with a girl on the beach2. Help models to work with high resolution - see the grid with totemhead-girl (it shows how PicX_real corrects a "broken" composition in realisticvision 5.1) and preview images number 5, 6, 7 (this all is native 1200px!)3. Improve output of models with LCM - see the grid with a girl with santa hatRecommended strength range is about 0.3 to 0.9, the exact value strongly depends on the method of application and the specific image, more often I use something around 0.5-0.8.I also recommend using this negative along with PicXer_real if you use it to fix high-resolution artifacts:[(CyberRealistic_Negative-neg, FastNegativeV2:0.8)::0.8], [(deformed, distorted, disfigured:1.25), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.3), disconnected limbs, mutation, mutated, disgusting, blurry, amputation::0.6], (epiCPhotoGasm-neg:0.6)PicXer_bside can:1. Make an image more darker/gloomy (0.5-1.5~ strength, grid)2. Improve concepts such as dark shot, horror, cyberpunk, abstraction, surrealism, fashion, glowing objects, etc. (1.0-2.0~ strenght)3. Help to see the "backside" of different models - an images with it will be significantly different from those without lora (1.5-2.0~ strength, grid)Recommended strength range is about 0.5 to 2.0, the exact value strongly depends on the specific goal (based on the above), more often I use something around 1.0-1.5.If you feel that your image is too noisy, I recommend trying "smoothing" upscalers for hires.fix: UniScale Balanced/UltraSharp/RealESRGAN.Any PicXer can't:1. Do miracles and make images good without your participation in generation process2. Improve an images without changing it, because it adds a PicX_real fraction to any model - this cannot go without changes, but by adjusting the strength of lora, you can choose the appropriate level of "change" for a particular image3. Fix to the end what sd 1.5 always torments us with - breaking hands, decreasing stability with increasing resolution, artifacts, etc. (but with skillful use it can reduce their number)It is forbidden to use it for any commercial purposes without my personal approval.
