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("Jonjew/ElleFanning")
prompt = "-"
image = pipe(prompt).images[0]Elle Fanning (FLUX + SDXL)
- Prompt
- -
Model description
FROM https://civitai.com/models/265004/elle-fanning-flux-sdxl?modelVersionId=884626
Strength 1 0.8-1.2. No keywords needed!
About this version
FLUX v1.0 :
Trained on FLUX dev with 70 photos of Elle Fanning with detailed captions. Tested on FLUX 1.D (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:
Positive : {Artstyle, Character and scene description in usual FLUX fashion}, <lora:ellefanning_local_flux_1_standard-000040:1>
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 19
Model tree for Jonjew/ElleFanning
Base model
black-forest-labs/FLUX.1-dev