SilverPulse Tech - World Morph - v1.0
精選圖片
推薦提示詞
a divin and futuristic Bear made of glossy silver and blue glow tech, delicate frame, cyborg, deus ex human revolution, futurisitc forest in background, SilverPulse, masterpiece, best quality, highly detailed, sharp focus, dynamic lighting
delicate frame, cyborg, deus ex human revolution, SilverPulse, masterpiece, best quality, highly detailed, sharp focus, dynamic lighting
推薦反向提示詞
text, watermark, low quality, worst quality, bad compostion, poor, low effort, child, childish, young, nude, nudity
text, watermark, low quality, worst quality, bad compostion, poor, low effort, (child, childish, young:1.2), nude, nudity, woman
推薦參數
samplers
steps
cfg
resolution
vae
提示
Use the trigger word 'SilverPulse' to activate the LoRA effect.
LoRA weight between 0.65 and 0.85 is recommended, but feel free to experiment.
ComfyUI settings used: Sampler dpmpp_3m_sde, cfg 3.6, Scheduler: Karras, Steps: 40.
For A1111 users, sampler DPM++ 3M Karras with cfg 3.6 and 40 steps is suggested.
Each image is generated at 1024x1024 resolution with no upscale.
Recommended VAE is the official sdxl_vae.
SilverPulse Tech - World Morph
Hello friends!
This LoRA is designed to get that futuristic sleek/glossy silver & blue glow.
Things To know:
You should use the trigger word SilverPulse
Usage Tips :
The LoRA weight I have been using is 0.65-0.85, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are:
Sampler: dpmpp_3m_sdecfg: 3.6
Scheduler: Karras
Steps: 40For A1111 enjoyers, I would use:
Sampler: DPM++ 3M Karras
cfg: 3.6
Steps: 40Example prompts used:
Prompt:"a divin and futuristic Bear made of glossy silver and blue glow tech, delicate frame, cyborg, deus ex human revolution, futurisitc forest in background, SilverPulse, masterpiece, best quality, highly detailed, sharp focus, dynamic lighting"
Negative prompt:"text, watermark, low quality, worst quality, bad compostion, poor, low effort, child, childish, young, nude, nudity"First image is with my LoRA and second is without my LoRA, same prompt and model.
Every picture is generated in 1024*1024 with no upscale
Recomended vae that I use is the official sdxl_vae
