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("ABGroup2/ImportLora")
prompt = "a pink crystal gem suspended in space, frstingln illustration"
image = pipe(prompt).images[0]Frosting Lane Flux
- Prompt
- a pink crystal gem suspended in space, frstingln illustration
- Negative Prompt
- bad, messy
- Prompt
- a man wearing a hunters cap frstingln illustration
- Negative Prompt
- bad, messy
- Prompt
- a beautiful castle frstingln illustration
- Negative Prompt
- bad, messy
- Prompt
- a small girl with a big grin, confident, on their toes, holding a sign that says "I LOVE PROMPTS!" frstingln illustration
- Negative Prompt
- bad, messy
Model description
Flux Dev training of my Frosting Lane Redux Model
Curious to see what ya'll think! I actually don't think the trigger makes a massive difference.
Trigger words
You should use frstingln illustration 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
- 3
Model tree for ABGroup2/ImportLora
Base model
black-forest-labs/FLUX.1-dev