Better Picture, More Details LoRA - v2
Related Keywords & Tags
Highlighted images
Recommended Prompts
masterpiece, highly detailed, 8k
Recommended Negative Prompts
watermark, (bad, ugly, amateur, sloppy, bad hands:1.1), mediocre, unorganized, simple, trivial, fingernail, crappy, grainy, grotesque, hobbyist, boring, childish, imbalance, disproportional, crossed, discord, unevenness, unnatural, mutated, haphazard, chaotic
Recommended Parameters
samplers
steps
cfg
Tips
Train images were downloaded from Pexels and carefully selected for sharpness and detail.
Images were cropped to improve composition and remove extra objects.
Images were processed with sharpening and saturation enhancement.
Image captions were generated using BLIP and WD14 models and merged.
Training was done using KohyaSS GUI with guidance from SECourses tutorial.
Tested using ComfyUI.
Version Highlights
Improved crispness and details in the images. The faces are improved too. Trained for 50% more epochs, this is a better version!
Make a better picture!
This LoRA will enhance your image in the following ways:
More details. You will notice that eyes, skin and hair have more details.
Sharpening. The image will have a sharper, crisper feel.
Better Composition! This LoRA was trained on professional photographs, which were cropped to improve composition. That helps in improving the composition.
This LoRA was trained in the following way:
Images were downloaded from Pexels website. The images were carefully selected to be sharp and have high details.
These images were cropped to improve composition and remove extra objects.
The images were processed. This meant image sharpening and enhancing image saturation wherever needed.
The images captions were generated using the KohyaSS Gui. I captioned the images two times, once using the BLIP model and the WD14 model. Then I merged the captions using a python script.
I used KohyaSS GUI to train the LoRA. Since I have a RTX 3060, I was barely able to train a LoRA by following the excellent tutorial by https://civitai.com/user/SECourses
I tested the LoRA with ComfyUI.
Contributor
Model Details
Discussion
Please log in to leave a comment.
