Instructions to use MarkBW/handbra-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarkBW/handbra-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/handbra-xl")

prompt = "UNICODE\u0000\u0000(\u0000c\u0000r\u0000o\u0000s\u0000s\u0000h\u0000a\u0000n\u0000d\u0000b\u0000r\u0000a\u0000)\u0000,\u0000 \u0000c\u0000h\u0000i\u0000a\u0000r\u0000o\u0000s\u0000c\u0000u\u0000r\u0000o\u0000 \u0000t\u0000e\u0000c\u0000h\u0000n\u0000i\u0000q\u0000u\u0000e\u0000 \u0000o\u0000n\u0000 \u0000s\u0000e\u0000n\u0000s\u0000u\u0000a\u0000l\u0000 \u0000i\u0000l\u0000l\u0000u\u0000s\u0000t\u0000r\u0000a\u0000t\u0000i\u0000o\u0000n\u0000 \u0000o\u0000f\u0000 \u0000a\u0000n\u0000 \u0000e\u0000l\u0000e\u0000g\u0000a\u0000n\u0000t\u0000 \u0000w\u0000o\u0000m\u0000a\u0000n\u0000,\u0000 \u0000m\u0000a\u0000t\u0000t\u0000e\u0000 \u0000p\u0000a\u0000i\u0000n\u0000t\u0000i\u0000n\u0000g\u0000,\u0000 \u0000b\u0000l\u0000o\u0000o\u0000m\u0000c\u0000o\u0000r\u0000e\u0000,\u0000 \u0000b\u0000y\u0000 \u0000H\u0000a\u0000n\u0000n\u0000a\u0000h\u0000 \u0000D\u0000a\u0000l\u0000e\u0000,\u0000 \u0000b\u0000y\u0000 \u0000H\u0000a\u0000r\u0000u\u0000m\u0000i\u0000 \u0000H\u0000i\u0000r\u0000o\u0000n\u0000a\u0000k\u0000a\u0000,\u0000 \u0000e\u0000x\u0000t\u0000r\u0000e\u0000m\u0000e\u0000l\u0000y\u0000 \u0000s\u0000o\u0000f\u0000t\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000s\u0000,\u0000 \u0000v\u0000i\u0000b\u0000r\u0000a\u0000n\u0000t\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000l\u0000y\u0000 \u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000,\u0000 \u0000d\u0000i\u0000g\u0000i\u0000t\u0000a\u0000l\u0000 \u0000a\u0000r\u0000t\u0000w\u0000o\u0000r\u0000k\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000 \u0000c\u0000o\u0000n\u0000t\u0000r\u0000a\u0000s\u0000t\u0000,\u0000 \u0000d\u0000r\u0000a\u0000m\u0000a\u0000t\u0000i\u0000c\u0000,\u0000 \u0000r\u0000e\u0000f\u0000i\u0000n\u0000e\u0000d\u0000,\u0000 \u0000t\u0000o\u0000n\u0000a\u0000l\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000c\u0000r\u0000o\u0000s\u0000s\u0000h\u0000a\u0000n\u0000d\u0000b\u0000r\u0000a\u0000_\u0000S\u0000D\u0000X\u0000L\u0000:\u00001\u0000>\u0000"
image = pipe(prompt).images[0]

Inference
Notebooks
Google Colab
Kaggle
Local Apps
Draw Things
DiffusionBee

handbra-xl

Prompt

UNICODE(crosshandbra), chiaroscuro technique on sensual illustration of an elegant woman, matte painting, bloomcore, by Hannah Dale, by Harumi Hironaka, extremely soft colors, vibrant, highly detailed, digital artwork, high contrast, dramatic, refined, tonal <lora:crosshandbra_SDXL:1>

Model description

Hands are problematic as always. Generate in batches! Keyword "crosshandbra"

Any description of clothes often nukes this one, panties excluded.

Include "topless" or "tits" if you aren't getting the effect.

By:jjjdddiop

Trigger words

You should use crosshandbra 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: 8

Model tree for MarkBW/handbra-xl

Base model

stabilityai/stable-diffusion-xl-base-1.0

Adapter

(8353)

this model