Text-to-Image
Diffusers
stable-diffusion
lora
template:sd-lora
migrated
cctv
style
security camera
surveillance
surveillance cam
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Norod78/cctv-stlye-sdxl")
prompt = "The girl with a pearl earring CCTV Style "
image = pipe(prompt).images[0]CCTV Stlye [SDXL]
- Prompt
- The girl with a pearl earring CCTV Style
- Prompt
- Footage of a woman who blankly gazing upon an alien performing a psychic attack CCTV Style
- Prompt
- Rick Sanchez CCTV Style
- Prompt
- A CCTV Style photo of carebear with a big gun
- Negative Prompt
- unrealistic, plastic, unfocused, grainy, blurry, monochrome
- Prompt
- A CCTV Style doorbell camera footage of the angel of death
- Prompt
- A CCTV Style photo of Cthulhu walking a watery street
- Negative Prompt
- unrealistic, plastic, unfocused, grainy, blurry, monochrome
- Prompt
- A creepy garden gnome CCTV Style
- Prompt
- A crazy clown CCTV Style
- Prompt
- Snoop Dogg CCTV Style
- Prompt
- Rick Sanchez CCTV Style
- Prompt
- Shrek and Olaf on a frozen field CCTV Style
- Negative Prompt
- blurry, unfocused, grainy, unrealistic
- Prompt
- A crazy clown CCTV Style
- Prompt
- A cute dog CCTV Style
- Negative Prompt
- blurry, unfocused, grainy, unrealistic
(CivitAI)
Model description
Trying to mimic the crappy yet unique style of CCTV cameras, the bad quality is a feature not a bug :) Hence, do not use to much negative and avoid Refiner / Too much of Hi-Rez fixes.
Trigger words
You should use CCTV Style 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
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/cctv-stlye-sdxl-sdv1-5', weight_name='SDXL-CCTV-Style-Lora.safetensors')
image = pipeline('A cute dog CCTV Style ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
- Downloads last month
- 29
Model tree for Norod78/cctv-stlye-sdxl
Base model
stabilityai/stable-diffusion-xl-base-1.0