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("cocktailpeanut/diddy")
prompt = "diddy smiling behind a man"
image = pipe(prompt).images[0]diddy
Trained with Fluxgym
- Prompt
- diddy smiling behind a man
- Prompt
- diddy wearing sunglasses standing at the corner of a nightclub, watching people
- Prompt
- diddy wearing sunglasses, on an escalator going up, smiling, staring at something
- Prompt
- smiling diddy wearing sunglasses, is holding johnson's baby oil bottle
Trigger words
You should use diddy to trigger the image generation.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
Weights for this model are available in Safetensors format.
- Downloads last month
- 26
Model tree for cocktailpeanut/diddy
Base model
black-forest-labs/FLUX.1-dev