Keltezaa/jennifer-carpenter-2012-flux-and-sdxl

Jennifer Carpenter 2012 Flux and SDXL

Prompt

woman, light makeup, sweater, smiling, kitchen

Prompt

woman, light makeup, sitting at a table wearing a light grey sweatshirt, holding a sign that has the handwriting "Welcome to FLUX!!" written on it. She is looking at the camera and in the background are some office plants on either side of her out of focus

Prompt

woman, light makeup, Expressionistic abstract painting utilizing a rough palette knife technique depicting the face of a woman with long flowing hair in the fall. The autumn theme is respresented through primary use of the colors red, orange and brown as well as autumn trees and leaves

Prompt

woman, light makeup,kodachrome, neon,cyberpunk, looking at viewer, frontview

Prompt

woman, light makeup, wearing a basketball jersey, at a basketball court, looking at camera

Model description

Flux

Jennifer Carpenter in 2012.. All sample images are with no face detailer or hi-res fix, they are 1024x1024 resolution. They are generated on Euler at 20 steps. This lora is trained on 1024x1024 resolution as well. I used flux dev in the sample images.I recommend putting "light makeup" some where in your prompt. I've done testing and there are 2 ways my loras usually work best:

1. Strength at 0.9-1 with no trigger word

2. Strength at 0.85-.0.95 with trigger word: c4rp3

i use comfy ui and theres a strength_clip option in the lora node and i set it to 0.85. Idk whats best but thats what i do

SDXL

Jennifer Carpenter in 2012. I recommend putting "light makeup" at the end of the prompt and seeing if it brings better results, if not just remove it. It depends on the checkpoint. This goes all my loras of women.

put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open

Trigger words

You should use c4rp3, light makeup 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

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/jennifer-carpenter-2012-flux-and-sdxl', weight_name='Jennifer_Carpenter_2012_Flux.safetensors')
image = pipeline('woman, light makeup, wearing a basketball jersey, at a basketball court, looking at camera').images[0]

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