Canopus-Realism-0.1

Prompt

A serious blond handsome man, lomography style photo, lomo camera style --ar 7:4 --v 5.1 --style raw --no watermarks

Prompt

A man with a beard and beanie tipped over his head, in the style of furaffinity, cory loftis, smilecore, polished craftsmanship, strong facial expression, alex russell flint, focus on joints/connections --ar 2:3 --v 5 --no hands

Prompt

Portrait of a beautiful woman with short hair wearing a a yellow sweater in the evening, with a blurred background and golden hour lighting, in the style of unsplash photography --ar 85:128 --v 6.0 --style raw

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases, better for realism based contextual prompting

Model description

prithivMLmods/Canopus-Realism-0.1

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	30 & 2500
Epoch	18	Save Every N Epochs	1

Trigger prompts

  A serious blond handsome man, lomography style photo, lomo camera style --ar 7:4 --v 5.1 --style raw --no watermarks

  A man with a beard and beanie tipped over his head, in the style of furaffinity, cory loftis, smilecore, polished craftsmanship, strong facial expression, alex russell flint, focus on joints/connections --ar 2:3 --v 5 --no hands
  
  Portrait of a beautiful woman with short hair wearing a a yellow sweater in the evening, with a blurred background and golden hour lighting, in the style of unsplash photography --ar 85:128 --v 6.0 --style raw

Parameter	Value
Prompt	Interinship, luxurious drapery, photo taken with provia --ar 128:85 --v 6.0 --style raw
Sampler	euler

Trigger words

You should use photorealistic to trigger the image generation.

You should use realism to trigger the image generation.

You should use realistic photography to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.