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("coyotle/90s_flash_photo")
prompt = "90s flash photo, lomography, analog photo, man and woman standing on the street, evening sky, half body shot, looking at viewer, <lora:90sflash_sdxl_v1:0.85>"
image = pipe(prompt).images[0]90s Flash Photo Style
- Prompt
- 90s flash photo, lomography, analog photo, man and woman standing on the street, evening sky, half body shot, looking at viewer, <lora:90sflash_sdxl_v1:0.85>
- Negative Prompt
- cartoon, illustration, anime, painting, CGI, 3D render, bad anatomy, bad hands, missing fingers, extra arms, text, numbers
- Prompt
- 90s flash photo, lomography, analog photo, a sad kid is sitting at the kitchen table with a cake in front of him, looking to viewer, <lora:90sflash_sdxl_v1:0.85>
- Negative Prompt
- cartoon, illustration, anime, painting, CGI, 3D render, bad anatomy, bad hands, missing fingers, extra arms, text, numbers, naked, nude
- Prompt
- 90s flash photo, lomography, light leak, analog photo, two girl hugs, selfie, looking at viewer, slim, <lora:90sflash_sdxl_v1:0.85>
- Negative Prompt
- cartoon, illustration, anime, painting, CGI, 3D render, bad anatomy, bad hands, missing fingers, extra arms, text, numbers, naked
Model description
LoRA for SDXL based on the aesthetics of 90s analog flash photography — harsh lighting, deep shadows, lomography-like colors.
Trigger words
90s flash photo90s photolight leakanalog photolomography
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 coyotle/90s_flash_photo
Base model
stabilityai/stable-diffusion-xl-base-1.0