license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- photorealistic
- female
- woman
- celebrity
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: kst3w
widget:
- text: 'kst3w, face, cap, sunglasses '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792607.jpeg
- text: 'kst3w, face, ponytail '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792610.jpeg
- text: 'kst3w, face, turtleneck '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792595.jpeg
- text: 'kst3w, face '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792598.jpeg
- text: 'kst3w, face,short blonde hair, white tank top, white shorts '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792603.jpeg
- text: 'kst3w, face '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792597.jpeg
- text: 'kst3w, face, sci-fi, cyberpunk, futuristic, depth of field '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792596.jpeg
- text: 'kst3w, face,blonde, leather jacket, white shirt, jeans '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792599.jpeg
- text: 'kst3w, face, flightsuit '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792602.jpeg
- text: 'kst3w, face, blonde hair '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792600.jpeg
- text: 'kst3w, face '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792601.jpeg
- text: 'kst3w, face, ponytail '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792604.jpeg
- text: 'kst3w, face,blonde, leather jacket, white shirt, jeans '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792605.jpeg
- text: 'kst3w, face, sci-fi, cyberpunk, futuristic, depth of field '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792606.jpeg
- text: 'kst3w, face,short blonde hair, white tank top, white shorts '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792609.jpeg
- text: 'kst3w, face, flightsuit '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792608.jpeg
- text: 'kst3w, face, sci-fi, cyberpunk, futuristic, depth of field '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792613.jpeg
- text: 'kst3w, face, turtleneck '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792612.jpeg
- text: 'kst3w, face, turtleneck '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792611.jpeg
- text: 'kst3w, face '
parameters:
negative_prompt: nsfw, lewd, child
output:
url: 4792614.jpeg
Kristen Stewart
Model description
LORA trained on 65 publicly available images of Kristen Stewart.
Trained on base SD 1.5, should work with most realistic models (works best with serenity v2).
Use ADetailer if details are lost and strength of 1 should work on most prompts.
Consider leaving a review if you like the model. All feedback is appreciated.
v1 - The likeness isn't as close as I wanted it to be, will revisit this model soon.
v2 is way better. Leaving both up - to show how big a difference can be made by changing repeats.
Trigger words
You should use kst3w
to trigger the image generation.
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
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to(device)
pipeline.load_lora_weights('Keltezaa/kristen-stewart', weight_name='kst3w-v2.safetensors')
image = pipeline('kst3w, face ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers