import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Jonjew/TerryFarrellEarly90s")
prompt = "a beautiful detailed high resolution photo of a woman wearing a traditional maid outfit with a maid headdress. The outfit is made of shiny silk and has puffy satin short sleeves. She is holding a tray and has a breaming smile at the viewer. <lora:Person_TerryFarrellH3-90s-FLUX:1>"
image = pipe(prompt).images[0]Terry Farrell Early 90s
- Prompt
- a beautiful detailed high resolution photo of a woman wearing a traditional maid outfit with a maid headdress. The outfit is made of shiny silk and has puffy satin short sleeves. She is holding a tray and has a breaming smile at the viewer. <lora:Person_TerryFarrellH3-90s-FLUX:1>
Model description
FROM https://civitai.com/models/1165254/terry-farrell-early-90s-or-fluxd?modelVersionId=1310853
Trigger a beautiful detailed high resolution photo, of a woman
Strength 1 Almost all generations ran with Flux.D BNB NF4 v2 on Forge with Diffusion in low bits set to FP16
Adetailer might help, might not.
Recommend prefixing with a beautiful detailed high resolution photo of a woman
90s Terry Farrell was something else. This is 100% taken from Hellraiser III screengrabs because I am probably clinically insane, or I desire consistency. Or both. Could be worse, I could have based all of them off the USA Red Dwarf Pilot...
Trigger words
You should use a beautiful detailed high resolution photo to trigger the image generation.
You should use of a woman to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 7
Model tree for Jonjew/TerryFarrellEarly90s
Base model
black-forest-labs/FLUX.1-dev