metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: >-
      an action shot of a knight fighting a giant fantasy ice phoenix, graveyard
      in background, Bosstyle, hkstyle, HD, masterpiece, best quality, hyper
      detailed, ultra detailed, super realistic
    parameters:
      negative_prompt: >-
        text, watermark, low quality, worst quality, bad compostion, poor, low
        effort, child, childish, young, 3d, 
    output:
      url: images/ComfyUI_12272_.jpeg
base_model: stabilityai/sdxl-turbo
instance_prompt: Bosstyle
license: cdla-permissive-2.0

XL_Boss_Battle_Sword

Prompt
an action shot of a knight fighting a giant fantasy ice phoenix, graveyard in background, Bosstyle, hkstyle, HD, masterpiece, best quality, hyper detailed, ultra detailed, super realistic

Negative Prompt
text, watermark, low quality, worst quality, bad compostion, poor, low effort, child, childish, young, 3d,

Model description

By HailoKnight

This LoRA is to make a cool boss fights, inspired by dark souls, elden ring and COD zombies. Im not that good at prompting, so will be cool to see what you can make!

If you like what I do feel free to support me on Ko-Fi☕ Things To know:

You should use the trigger word Bosstyle

This lora worked really good with my Fantasty Knight LoRA, it added good details and better bosses for some reason!!

Usage Tips :

The LoRA weight I have been using is 0.85, 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: 50

For A1111 enjoyers, I would use:
Sampler: DPM++ 2M Karras
Steps: 50

Example prompts used:

&quot;an action shot of a knight fighting a giant black fantasy lion, graveyard in background&quot;

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 and with the model Unstable Diffusior V11

Recomended vae that I use is the official sdxl_vae

Please enjoy and share your amazing work!

Trigger words

You should use Bosstyle to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.