base_LoRA_512_512_bs6_step200

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

SDXL LoRA - NLPBada/base_LoRA_512_512_bs6_step200

<Gallery />

Model description

These are NLPBada/base_LoRA_512_512_bs6_step200 LoRA adaption weights for OnomaAIResearch/Illustrious-xl-early-release-v0.

The weights were trained using

LoRA for the text encoder was enabled: False.

Special VAE used for training: None.

Trigger words

You should use ""In the style of irasutoya," to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Intended uses & limitations

How to use

#Adjusted guidance_scale + Negative Prompt
width = 1024 
height = 1024 
num_inference_steps = 60 
guidance_scale = 5.5 
# prompt = "In the style of irasutoya, 1girl, lightblue collared shirt, smiling with mouth closed, wearing glasses, eyes not visible, furrowed eyebrows, black bobbed parted hair" # @param
prompt = "In the style of irasutoya a boy wearing a darkcyan shirt, smiling with mouth closed, furrowing eyebrows, black pouty hair, upper body" # @param
negative_prompt = "duplicates, worst quality, bad quality, low quality, scan artifacts, jaggy lines, unclear" #@param

image = pipe(prompt, num_inference_steps=num_inference_steps, width=width, height=height, guidance_scale=guidance_scale).images[0]
image

Limitations and bias

pending

Training details

pending