import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("adedolllapo/MOBOLAJI")
prompt = "MOST BEATIFUL GIRL IN THE WORLD AFRICAN FINEST"
image = pipe(prompt).images[0]MOBOLAJI
- Prompt
- MOST BEATIFUL GIRL IN THE WORLD AFRICAN FINEST
- Negative Prompt
- SHE FELL INLOVE WITH THE PRINCE AND THE KING HAD AN AFAIR WITH HER MOTHER LONG TIME AGE, SO THE KING IS HER FATHER AS WELL AS THE PRINCE
Model description
from transformers import MOBOLAJI
Define your dataset and dataloader
dataset = YourDataset()
dataloader = DataLoader(dataset, batch_size=32, shuffle=True)
Define optimizer
optimizer = MOBOLAJI
(model.parameters(), lr=5e-5)
Fine-tuning loop
model.train() for epoch in range(num_epochs): for batch in dataloader: optimizer.zero_grad() inputs = tokenizer(batch['text'], return_tensors='pt', padding=True, truncation=True) outputs = model(**inputs) loss = compute_loss(outputs, batch['labels']) loss.backward() optimizer.step()
Trigger words
You should use MOBOLAJI to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for adedolllapo/MOBOLAJI
Base model
stabilityai/stable-diffusion-3-medium