Instructions to use Apocalypse-19/Vishu-the-Cat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Apocalypse-19/Vishu-the-Cat with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Apocalypse-19/Vishu-the-Cat", dtype=torch.bfloat16, device_map="cuda") prompt = "A photo of vishu cat" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Dreambooth Model for Animals trained on a custom dataset.
This is a Stable Diffusion model fine-tuned on the animal concept with DreamBooth. It can be used by modifying the instance_prompt: A photo of vishu cat
This model was created as part of the DreamBooth Hackathon 🔥.
Description
Model finetuned on the pictures of our cat named Vishu, made for the Dreambooth Hackathon, finetuned on Stable diffusion 2.1 Base
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('Apocalypse-19/Vishu-the-Cat')
image = pipeline().images[0]
image
Examples
Some examples of images generated with their prompts are (Guidance scale = 7.5 and Number of Inference steps = 50 for all):
Prompt = A photo of vishu cat as a genshin impact character

Prompt = A photo of vishu cat shaking hands with Donald Trump

- Downloads last month
- 5

