---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: MOST BEATIFUL GIRL IN THE WORLD AFRICAN FINEST
  parameters:
    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
  output:
    url: >-
      images/Default_African_Story_YouTube_page_featuring_a_stunning_illust_1.jpg
base_model: stabilityai/stable-diffusion-3-medium
instance_prompt: MOBOLAJI
license: afl-3.0
---
# MOBOLAJI

<Gallery />

## Model description 

from transformers import MOBOLAJI

# Define your dataset and dataloader
# dataset &#x3D; YourDataset()
# dataloader &#x3D; DataLoader(dataset, batch_size&#x3D;32, shuffle&#x3D;True)

# Define optimizer
optimizer &#x3D; MOBOLAJI
![Default_African_Story_YouTube_page_featuring_a_stunning_illust_1 (1).jpg](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;667d89fd77b387232c35dd00&#x2F;wWvz-vkTNWsqtUL7Kdl30.jpeg)
(model.parameters(), lr&#x3D;5e-5)

# Fine-tuning loop
model.train()
for epoch in range(num_epochs):
    for batch in dataloader:
        optimizer.zero_grad()
        inputs &#x3D; tokenizer(batch[&#39;text&#39;], return_tensors&#x3D;&#39;pt&#39;, padding&#x3D;True, truncation&#x3D;True)
        outputs &#x3D; model(**inputs)
        loss &#x3D; compute_loss(outputs, batch[&#39;labels&#39;])
        loss.backward()
        optimizer.step()


## Trigger words

You should use `MOBOLAJI` to trigger the image generation.


## Download model


[Download](/adedolllapo/MOBOLAJI/tree/main) them in the Files & versions tab.