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("TonyBaloney/HalleBerryOverfittedv2")
prompt = "-"
image = pipe(prompt).images[0]Halle Berry 90s v2
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
My 2nd attempt at making Halle Berry FLUX LoRA. Came out better than version, but still heavily overfitted. More post-processing needed
Trigger words
You should use berry90v2 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
- 6
Model tree for TonyBaloney/HalleBerryOverfittedv2
Base model
black-forest-labs/FLUX.1-dev