SheepsControlV1 / README.md
GreeneryScenery's picture
Update README.md
b457f80
|
raw
history blame
887 Bytes
---
datasets:
- GreeneryScenery/SheepsNet
pipeline_tag: image-to-image
tags:
- ControlNet
---
# V1
First try at training a custom [ControlNet](https://github.com/huggingface/diffusers/tree/main/examples/controlnet). (Only 1 epoch 🤗) Using dataset from [here](https://huggingface.co/datasets/GreeneryScenery/SheepsNet).
Follow [this](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/controlnet) to use (u sure ya wanna use?).
Things to improve:
- More variety of data in general? (Not only sheeps)
- More data (More sheeps)
- More epochs
- Better text prompts
## Example:
Prompt: Lamb
Conditioning image:
<img src = 'https://huggingface.co/GreeneryScenery/SheepsControl/resolve/main/example_input.png' style = 'width: 256px'>
Image:
<img src = 'https://huggingface.co/GreeneryScenery/SheepsControl/resolve/main/example_output.png' style = 'width: 256px'>