Instructions to use hgutjh/DeArm3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hgutjh/DeArm3 with Diffusers:
pip install -U diffusers transformers accelerate
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("hgutjh/DeArm3") prompt = "UNICODE\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000a\u0000n\u0000a\u0000_\u0000d\u0000e\u0000_\u0000a\u0000r\u0000m\u0000a\u0000s\u0000_\u0000d\u0000e\u0000v\u0000_\u0000f\u00001\u0000:\u00001\u0000>\u0000 \u0000a\u0000n\u0000a\u0000 \u0000a\u0000 \u0000b\u0000e\u0000a\u0000u\u0000t\u0000i\u0000f\u0000u\u0000l\u0000 \u0000w\u0000o\u0000m\u0000a\u0000n\u0000,\u0000 \u0000f\u0000u\u0000l\u0000l\u0000 \u0000b\u0000o\u0000d\u0000y\u0000 \u0000i\u0000m\u0000a\u0000g\u0000e\u0000,\u0000 \u0000w\u0000e\u0000a\u0000r\u0000i\u0000n\u0000g\u0000 \u0000v\u0000i\u0000n\u0000t\u0000a\u0000g\u0000e\u0000 \u0000c\u0000l\u0000o\u0000t\u0000h\u0000i\u0000n\u0000g\u0000,\u0000 \u0000t\u0000u\u0000r\u0000t\u0000l\u0000e\u0000 \u0000n\u0000e\u0000c\u0000k\u0000 \u0000s\u0000w\u0000e\u0000a\u0000t\u0000e\u0000r\u0000,\u0000 \u0000o\u0000u\u0000t\u0000s\u0000i\u0000d\u0000e\u0000,\u0000 \u0000i\u0000m\u0000a\u0000g\u0000e\u0000 \u0000s\u0000h\u0000o\u0000t\u0000 \u0000o\u0000n\u0000 \u0000f\u0000i\u0000l\u0000m\u0000,\u0000 \u0000f\u0000a\u0000d\u0000e\u0000,\u0000 \u0000l\u0000i\u0000g\u0000h\u0000t\u0000 \u0000l\u0000e\u0000a\u0000k\u0000,\u0000 \u0000a\u0000r\u0000t\u0000i\u0000s\u0000t\u0000i\u0000c\u0000,\u0000 \u0000b\u0000e\u0000a\u0000u\u0000t\u0000i\u0000f\u0000u\u0000l\u0000,\u0000 \u0000s\u0000h\u0000o\u0000p\u0000s\u0000,\u0000 \u0000g\u0000l\u0000a\u0000s\u0000s\u0000,\u0000 \u0000c\u0000o\u0000n\u0000c\u0000r\u0000e\u0000t\u0000e\u0000,\u0000 \u0000d\u0000e\u0000s\u0000i\u0000g\u0000n\u0000,\u0000 \u0000t\u0000h\u0000o\u0000u\u0000g\u0000h\u0000t\u0000f\u0000u\u0000l\u0000" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
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("hgutjh/DeArm3")
prompt = "UNICODE\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000a\u0000n\u0000a\u0000_\u0000d\u0000e\u0000_\u0000a\u0000r\u0000m\u0000a\u0000s\u0000_\u0000d\u0000e\u0000v\u0000_\u0000f\u00001\u0000:\u00001\u0000>\u0000 \u0000a\u0000n\u0000a\u0000 \u0000a\u0000 \u0000b\u0000e\u0000a\u0000u\u0000t\u0000i\u0000f\u0000u\u0000l\u0000 \u0000w\u0000o\u0000m\u0000a\u0000n\u0000,\u0000 \u0000f\u0000u\u0000l\u0000l\u0000 \u0000b\u0000o\u0000d\u0000y\u0000 \u0000i\u0000m\u0000a\u0000g\u0000e\u0000,\u0000 \u0000w\u0000e\u0000a\u0000r\u0000i\u0000n\u0000g\u0000 \u0000v\u0000i\u0000n\u0000t\u0000a\u0000g\u0000e\u0000 \u0000c\u0000l\u0000o\u0000t\u0000h\u0000i\u0000n\u0000g\u0000,\u0000 \u0000t\u0000u\u0000r\u0000t\u0000l\u0000e\u0000 \u0000n\u0000e\u0000c\u0000k\u0000 \u0000s\u0000w\u0000e\u0000a\u0000t\u0000e\u0000r\u0000,\u0000 \u0000o\u0000u\u0000t\u0000s\u0000i\u0000d\u0000e\u0000,\u0000 \u0000i\u0000m\u0000a\u0000g\u0000e\u0000 \u0000s\u0000h\u0000o\u0000t\u0000 \u0000o\u0000n\u0000 \u0000f\u0000i\u0000l\u0000m\u0000,\u0000 \u0000f\u0000a\u0000d\u0000e\u0000,\u0000 \u0000l\u0000i\u0000g\u0000h\u0000t\u0000 \u0000l\u0000e\u0000a\u0000k\u0000,\u0000 \u0000a\u0000r\u0000t\u0000i\u0000s\u0000t\u0000i\u0000c\u0000,\u0000 \u0000b\u0000e\u0000a\u0000u\u0000t\u0000i\u0000f\u0000u\u0000l\u0000,\u0000 \u0000s\u0000h\u0000o\u0000p\u0000s\u0000,\u0000 \u0000g\u0000l\u0000a\u0000s\u0000s\u0000,\u0000 \u0000c\u0000o\u0000n\u0000c\u0000r\u0000e\u0000t\u0000e\u0000,\u0000 \u0000d\u0000e\u0000s\u0000i\u0000g\u0000n\u0000,\u0000 \u0000t\u0000h\u0000o\u0000u\u0000g\u0000h\u0000t\u0000f\u0000u\u0000l\u0000"
image = pipe(prompt).images[0]DeArm3

- Prompt
- UNICODE<lora:ana_de_armas_dev_f1:1> ana a beautiful woman, full body image, wearing vintage clothing, turtle neck sweater, outside, image shot on film, fade, light leak, artistic, beautiful, shops, glass, concrete, design, thoughtful
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 7