metadata
license: creativeml-openrail-m
base_model:
- stabilityai/stable-diffusion-xl-base-1.0
pipeline_tag: text-to-image
tags:
- lora
- stable-diffusion
- text-to-image
Model Description
This model is a fine-tuned Stable Diffusion model trained to generate cartoon/anime-style characters in different outfits, roles, and professions. The outputs are vibrant, colorful, and suitable for illustrations, educational content, and storytelling.
Intended Uses
- Creating illustrations for children’s books.
- Designing characters for storytelling, comics, or animations.
How to Use
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("username/LingoSpace", torch_dtype=torch.float16).to("cuda")
prompt = "a cartoon cat dressed as a firefighter, standing in front of a fire truck"
image = pipe(prompt).images[0]
image.save("cat_firefighter.png")
Prompt Examples
- cartoon cat in a space suit is a firefighter
- cartoon cat in a space suit with an ambulance
- cartoon cat in a space suit eating popcorn and watching a movie
- cartoon cat in a space suit looking at a cell phone
- cartoon cat in a space suit pressing a big button
- cartoon cat in a space suit is very old
- cartoon cat in a space suit is exercising in the gym
- cartoon cat in a space suit with his child
- cartoon cat in a space suit wakes up