Shoutout to our Discord community over at AIpub come and join us!❤️
You should use the trigger words Sniper Rifle (For best results)
90% of the dataset images are of people laying down so for best result prompt that. But feel free to try it out.
The LoRA weight I have been using is 0.85-1, but feel free to try and experiment!
ComfyUI settings im using are:
Sampler: dpmpp_2m
Scheduler: Karras
Steps: 30
For A1111/Forge enjoyers, I would use:
Sampler: Euler A
Scheduler: Normal
Steps: 50
Example prompts used:
"Flatline, Flat vector illustration,,masterpiece, best quality, good quality, very aesthetic, absurdres, newest, 8K, depth of field, focused subject,
dynamic angle, close up, b0nz1buddy, gorilla, holding a purple glowing sniper rifle, laying on the ground, aiming at the viewer, glowing ethereal light, battlefield in background"
First image is with my LoRA and second is without my LoRA, same prompt and model.
The LoRA weight I have been using is 0.85-1, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are:
Sampler: dpmpp_2m
Scheduler: Karras
Steps: 30
For A1111 enjoyers, I would use:
Sampler: DPM++ 2M Karras
Steps: 30
Example prompts used:
"score_9, score_8_up, score_7_up, upscale 2x, (a realistic action shot of a soldier wielding an (sniper rifle made of ice, pointing at the camera, wearing white armor, snowing, snow mountains in background:1.3):1.2)"
First image is with my LoRA and second is without my LoRA, same prompt and model.
Recomended vae that I use is the official sdxl_va