metadata
license: creativeml-openrail-m
tags:
- pytorch
- diffusers
- stable-diffusion
- text-to-image
- diffusion-models-class
- dreambooth-hackathon
- wildcard
widget:
- text: a pkblz ball in the middle of a miniature jungle
DreamBooth model for the pkblz (pokeball) concept trained by simonschoe on a dataset of basic pokeball (the plain white-red one) images.
This is a Stable Diffusion model fine-tuned on the pkblz (pokeball) concept with DreamBooth. It can be used by modifying the instance_prompt: a pkblz ball in the middle of a miniature jungle
This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!
Training Details:
- Number of training images: 31
- Learning rate: 2e-06
- Training steps: 800
- Guidance Scale: 10
- Inference Steps: 75
| Prompt | Prompt | Prompt |
.png) |
.png) |
.png) |
| Prompt | Prompt | Prompt |
.png) |
.png) |
.png) |
| Prompt | Prompt | Prompt |
.png) |
.png) |
.png) |
Description
This is a Stable Diffusion model fine-tuned on (poke)ball images for the wildcard theme.
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('simonschoe/pokeball-machine')
image = pipeline().images[0]
image