Instructions to use MarkBW/phone-exposure-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MarkBW/phone-exposure-xl with Diffusers:
pip install -U diffusers transformers accelerate
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("MarkBW/phone-exposure-xl") prompt = "UNICODE\u0000\u00001\u0000g\u0000i\u0000r\u0000l\u0000,\u0000 \u0000o\u0000f\u0000f\u0000i\u0000c\u0000e\u0000 \u0000l\u0000a\u0000d\u0000y\u0000,\u0000 \u0000l\u0000o\u0000n\u0000g\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000s\u0000t\u0000a\u0000n\u0000d\u0000i\u0000n\u0000g\u0000,\u0000 \u0000o\u0000f\u0000f\u0000i\u0000c\u0000e\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00009\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00008\u0000_\u0000u\u0000p\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00007\u0000_\u0000u\u0000p\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00006\u0000_\u0000u\u0000p\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00005\u0000_\u0000u\u0000p\u0000,\u0000 \u0000s\u0000c\u0000o\u0000r\u0000e\u0000_\u00004\u0000_\u0000u\u0000p\u0000,\u0000 \u0000p\u0000h\u0000o\u0000n\u0000e\u0000,\u0000 \u0000s\u0000c\u0000r\u0000e\u0000e\u0000n\u0000,\u0000 \u0000f\u0000u\u0000l\u0000l\u0000y\u0000 \u0000c\u0000l\u0000o\u0000t\u0000h\u0000e\u0000d\u0000,\u0000 \u0000p\u0000h\u0000o\u0000n\u0000e\u0000 \u0000e\u0000x\u0000p\u0000o\u0000s\u0000u\u0000r\u0000e\u0000,\u0000 \u0000g\u0000a\u0000r\u0000t\u0000e\u0000r\u0000 \u0000s\u0000t\u0000r\u0000a\u0000p\u0000s\u0000,\u0000 \u0000g\u0000a\u0000r\u0000t\u0000e\u0000r\u0000b\u0000e\u0000l\u0000t\u0000,\u0000 \u0000l\u0000i\u0000n\u0000g\u0000e\u0000r\u0000i\u0000e\u0000,\u0000 \u0000b\u0000r\u0000a\u0000,\u0000 \u0000n\u0000u\u0000d\u0000e\u0000,\u0000 \u0000f\u0000i\u0000r\u0000s\u0000t\u0000 \u0000p\u0000e\u0000r\u0000s\u0000o\u0000n\u0000 \u0000v\u0000i\u0000e\u0000w\u0000,\u0000 \u0000w\u0000h\u0000i\u0000t\u0000e\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000P\u0000h\u0000o\u0000n\u0000e\u0000E\u0000x\u0000p\u0000o\u0000s\u0000u\u0000r\u0000e\u0000P\u0000o\u0000n\u0000y\u0000X\u0000L\u0000:\u00001\u0000>\u0000,\u0000 \u0000s\u0000k\u0000i\u0000m\u0000p\u0000y\u0000" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
phone-exposure-xl

- Prompt
- UNICODE1girl, office lady, long hair, standing, office, score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, phone, screen, fully clothed, phone exposure, garter straps, garterbelt, lingerie, bra, nude, first person view, white hair, <lora:PhoneExposurePonyXL:1>, skimpy
Model description
This lora aims to create images of characters in a sfw settings, while the viewer holds a phone depicting them in a not so sfw situation.
I recommend a weight of 1.0 to 1.2. Works decently at any width and height, start with 896x1152.
Trigger words are 'phone exposure' and 'phone pov'.
Is able to do anime and furry characters, is decent with character and style loras as well.
Works most of the time, though I will probably retrain at a later time with better parameters and data, and reduce the size too.
By:ArtificalisAnima
Trigger words
You should use phone exposure to trigger the image generation.
You should use phone pov 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
- 10