metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - style
  - glow
  - rim light
  - protodarkglow
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: null
widget:
  - text: ' '
    output:
      url: 6229263.jpeg
  - text: ' '
    output:
      url: 6229429.jpeg
  - text: ' '
    output:
      url: 6244384.jpeg

ProtoDarkGlow

Model description

Originally I retrained a data set for a model that was exclusive to DiffusionBee (you can find that "darkglowstyle" model along with a few others here https://huggingface.co/brushpenbob/DiffusionBee/tree/main but again that file format is unique to DiffusionBee) this is a LoRa created with the same Data set in CivitAI, - see walkthrough video below.

It can be a bit heavy handed so you can have some leniency with weight. in my demo im ising a weight of 1 but a little trial and error you might find what works best for your needs

Using SD 1.5 as its base and a series of glowing / bio luminescent style art it was trained to give your image that bit of glow its missing

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('brushpenbob/protodarkglow', weight_name='ProtoDarkGlow.safetensors')
image = pipeline('Your custom prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers