CCMat's picture
Update README.md
6e5b02d
metadata
license: creativeml-openrail-m
tags:
  - pytorch
  - diffusers
  - stable-diffusion
  - text-to-image
  - diffusion-models-class
  - dreambooth-hackathon
  - animal
widget:
  - text: a photo of fluffalpaca llama in front of the Colosseum in Rome

DreamBooth model for the fluffalpaca concept trained on the CCMat/db-aplaca dataset.

This is a Stable Diffusion model fine-tuned on the fluffalpaca concept with DreamBooth. It can be used by modifying the instance_prompt: a photo of fluffalpaca llama

This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!

Description

This is a Stable Diffusion model fine-tuned on llama images for the animal theme.

Training Hyperparemeters

Pretrained Model: stabilityai/stable-diffusion-2
Learning rate: 1e-6
Steps:1100

Usage

from diffusers import StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_pretrained('CCMat/fluffalpaca-llama-1100')
image = pipeline().images[0]
image

Samples

Prompt: "fluffalpaca llama in space by Enki Bilal" example images

Prompt: "fluffalpaca llama in front of the Eiffel Tower" example images

Prompt: "a photo of fluffalpaca llama swimming in the river" example images

Prompt: "a photo of fluffalpaca llama in front of the Colosseum in Rome, professional photograph" example images

Prompt: "USSR propoganda poster. Long live the fluffalpaca llama" example images