FIRST OF ALL: I ASK THAT IF YOU USE MY LORA, PLEASE DO NOT PUBLISH NSFW CONTENT THAT IS DAMAGING, ABUSIVE, DEGRADING, INSULTING, HUMILIATING, OR OFFENSIVE TO HUMAN DIGNITY. I DID NOT CREATE MY LORAS FOR PEOPLE TO DO SUCH THINGS. PLEASE, BE RESPECTFUL.
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
This LoRa is designed to generate creative images with styles that blend graphic design with a strong influence from vector art and a touch of ink. If you want to create unpredictable images with unusual designs, you may find this LoRa interesting.
NOTE: Feel free to try out this LoRa as much as you like, and if you wish, you are totally free to write your opinions and recommendations in the comments. It would be greatly appreciated.
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Suggested Specifications:
Image size: 768x1360.
Sampling Steps: 20 to 30. But it can easily be done in 8 steps if you use the LoRa “Qwen-Image Lightning - 8steps-V1.1,” which is very helpful. (Thanks to @Kei for the recommendation)
VAE: Automatic.
Sampling Method: "uni_pc" sampler; with "ddim_uniform" scheduler (you can use any sampler you prefer, just make sure to use the TA information table for the best results).
CFG Scale: 1
Base Model: Qwen-Image.
Well, lastly, I hope this model helps you create the images you want and that you enjoy it. If you have any questions, feel free to write in the comments.