CoolFace
Modelpublic

Keltezaa/garbage-patch

sourceHugging Faceotherupdated 2y agoView on Hugging Face
3likes19downloads
Model Card

garbage patch

<Gallery />

(CivitAI)

Model description

<p><span style="color:rgb(193, 194, 197)">Try size: 512 x 768 or 768 x 1024 or above</span></p><p><span style="color:rgb(193, 194, 197)">Weights: 0.8 (BlondehairFlux: The background is Less detailed, but suitable for blonde hair / BlackhairFlux: If weights is 1.0, the background is too bright)</span></p><p><span style="color:rgb(193, 194, 197)">Training material from ChilloutMix and Koreandolllikeness</span></p><p></p><p><span style="color:rgb(193, 194, 197)">Note: The blue eyes and blond hair are placed forward, closer to the appearance of a western female. (BlondehairFlux)</span></p><p></p><p><span style="color:rgb(193, 194, 197)">Note: Occasionally there will be watermarks, no blond hair to choose from, too many boats. (BlackhairFlux)</span></p><p></p><p><span style="color:rgb(193, 194, 197)">("garbage patch" is not a very precise model title, but we can focus on protecting marine ecology. It is usually located in the open ocean and not so close to the land)</span></p>

Trigger words

You should use garbage patch, realistic, blue eyes, blonde hair, smile, 1girl, a pretty woman, slim figure, facial features, thick lips, absurdly long hair, floating hair, nude, naked, nipples, areola, large breasts, wind, ocean, backwash, post-apocalypse, partially submerged in water, wading, wet, trash, rubbish, night, moon, shore lights, 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

py
from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/garbage-patch', weight_name='garbagepatch_blondehair_flux.safetensors')
image = pipeline('garbage patch, realistic, blue eyes, blonde hair, smile, sitting, 1girl, a pretty woman, slim figure, facial features, thick lips, absurdly long hair, floating hair, nude, naked, nipples, areola, large breasts, wind, ocean, backwash, post-apocalypse, partially submerged in water, wading, wet, trash, rubbish, night, moon, shore lights, ').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers