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("Akbartus/FluxHandDrawnVectorStyle_LORA")
prompt = "fla8"
image = pipe(prompt).images[0]Basic Prompt Structure:
Character Description: Describe the character you want to create (e.g., “a cute bunny,” “a joyful crocodile”).
Style: Always include “hand drawn vector style” to ensure the LoRa applies the correct artistic style.
Pose/Expression: Mention the character’s pose or expression to add more personality (e.g., “waving at the viewer,” “walking with a big smile”).
Colors: You can specify colors or extra details if needed (e.g., “bright yellow with pink accents,” “Tritone color Scheme”).
Example Prompts:
"A cute bunny character, hand drawn vector style, cheerful expression, waving at the viewer."
"A happy ice cream character, hand drawn vector style, with a cherry on top, tongue sticking out."
"A playful cat character, hand drawn vector style, bright yellow and pink, walking forward."
- Downloads last month
- 9
Model tree for Akbartus/FluxHandDrawnVectorStyle_LORA
Base model
black-forest-labs/FLUX.1-dev