Your voice matters! Show your support by leaving a post, comment or review! ⭐
Custom LoRAs available upon request. Just buymeacoffee.☕
This is a + LoRA! (details in workflow advice below) 👇
born on September 8, 1990, in Tochigi, Japan, is a former Japanese actress and model. She went by various aliases such as Megumi Shino, Aoi Myajima and Haruka Nakamura. She started her career in the entertainment industry in 2010, at the age of 20, with the film studio 'Marx Brothers.' After that, she worked with other film studios such as Sky High Entertainment, Idea P., and Rocket. Shino was primarily known for her work in videos and web scenes, and she also performed in videos with other famous actresses such as Yui Hatano and Shizuka Kanno.
Shino Aoi was 5 feet 4 inches (163 cm) tall and weighed 101 lbs (46 kg) with a slim build. She has dark brown eyes and hair. Her body measurements are 31A-23-30, and she wears a dress size of 36 (EU) and shoe size 7. Shino enjoys cooking, giving massages. Additionally she enjoys traveling, shopping, taking selfies, and internet surfing.
Shino retired from the entertainment industry in 2020 after ten years of working in the business. She has left a significant mark on the industry during her time as an actress and model. Her performances in various videos and web scenes have garnered her a large following of fans, and she remains a popular figure in the adult entertainment industry.
What's the + for?
Just an easy way to indicate the dataset image for this particular LORA was based off a minimum of 1024px+ quality source images with the LORA trained at 1024,1024 (I may go higher in the future if I can get a properly working configuration).
For the most part, you can start with higher base resolutions to capture more details and/or generate higher quality outputs. See some of the gallery examples.
You don't have to gen at high resolution, low res generations will be better quality as well.
Most images have been generated with LORA weighted @ .9 - 1.
For photoreal shots, I've found sampling steps best well above 50 give better results.
ControlNet is your friend. Embrace the dark side.😈
Tile pre-sample and model is good for extreme close ups
I use segmentation for lots of my generations now.
This + series is something new, let me know if I should take the extra time it takes to create these type of LoRAs or just stick with the regular quality.
Help me help you: Leave a review if you've used this LORA.
Most of my gens are not voodoo or outside of workflows I've indicated here or in my other posts.
In other words: Leave a comment if you are having issues getting good output, I'll try to respond with suggestions.