Image-to-Image
English
stable-diffusion
controlnet
controlnet-v1-seg / README.md
lavinal712's picture
Update README.md
591d167 verified
---
license: mit
datasets:
- Levi980623/ControlNet_ade20k
- mfidabel/sam-coyo-3k
- lmms-lab/COCO-Caption2017
pipeline_tag: image-to-image
language:
- en
tags:
- stable-diffusion
- controlnet
---
# Model Card for lavinal712/controlnet-v1-seg
## Model Description
This is controlnet weight trained on runwayml/stable-diffusion-v1-5 with segmentaion.
### Training
This model was trained using a Segmented dataset based on the ADE20k Dataset, COYO-700M Dataset and COCO Dataset. Stable Diffusion v1.5 checkpoint was used as the base model for the controlnet.
- [ControlNet-ade20k](https://huggingface.co/datasets/Levi980623/ControlNet_ade20k)
- [SAM-COYO-3k](https://huggingface.co/datasets/mfidabel/sam-coyo-3k)
- [COCO2017](https://huggingface.co/datasets/lmms-lab/COCO-Caption2017)
#### Training Method
- Train on [ControlNet-ade20k](https://huggingface.co/datasets/Levi980623/ControlNet_ade20k) for 30 epochs.
- Train on [SAM-COYO-3k](https://huggingface.co/datasets/mfidabel/sam-coyo-3k) for 30 epochs.
- Train on [COCO2017](https://huggingface.co/datasets/lmms-lab/COCO-Caption2017) for 1 epoch.