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("youngho79/youngho")
prompt = "A middle-aged Korean man in a white shirt and navy suit, standing confidently in a modern office with large windows, photorealistic, natural lighting, sharp focus <youngho79>"
image = pipe(prompt).images[0]youngho
- Prompt
- A middle-aged Korean man in a white shirt and navy suit, standing confidently in a modern office with large windows, photorealistic, natural lighting, sharp focus <youngho79>
- Negative Prompt
- blurry, distorted, extra limbs, out of focus, low resolution
Model description
Fine-tuned LoRA for consistent face, white shirt, and navy jacket.
Trigger words
You should use youngho to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 2
Model tree for youngho79/youngho
Base model
black-forest-labs/FLUX.1-dev