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("Keltezaa/LiquidFlowStyle")
prompt = "tall Male Scientist, the Scientist is dressed in Expressionism fashion style ral-watce, <lora:LiquidFlowStyle:1.25>, shiny, contemporary, extremely rich detail, cute, creative, sunny, highly complex, aesthetic, best, excellent composition, confident"
image = pipe(prompt).images[0]Liquid Flow Style
- Prompt
- tall Male Scientist, the Scientist is dressed in Expressionism fashion style ral-watce, <lora:LiquidFlowStyle:1.25>, shiny, contemporary, extremely rich detail, cute, creative, sunny, highly complex, aesthetic, best, excellent composition, confident
Trigger words
You should use ral-watce 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
- 23
Model tree for Keltezaa/LiquidFlowStyle
Base model
black-forest-labs/FLUX.1-dev