This is a Midjourney Cinematic style Lora based on my aesthetics. Adds cinematic vibe and also additional detailing to a broad range of image themes without too much bias towards a single style.
Version 1: Trained on R128, 40 Images, 5000 Steps
Future Versions: When I get enough buzz I'll train more and even better loras!
WORKFLOW UPDATE v3.5: Added Upscaler, and improved sampler type quality.
NOTE: For Large Upscale, if getting double images, lower denoise a bit.
Discovered trick for workflow to get quality of high steps, without doing the steps. (v3+ workflow)
Needed Nodes: 1) https://github.com/erosDiffusion/ComfyUI-EulerDiscreteScheduler
2) https://github.com/ClownsharkBatwing/RES4LYF
Recommendation: (Keep lora strength lower @ 0.2 to 0.5 !!!)
This is my very first Lora, hope you like it! Special thx to: @PastellPastellPastellI
Lora Strength Comparisons Below:
