Downloads · 30 days
0
controlnet-v1-seg
lavinal712/controlnet-v1-seg
controlnet-v1-seg is a image-to-image model from lavinal712. Use it when you need one image transformed into another. The card lists the license as mit.
This is controlnet weight trained on runwayml/stable-diffusion-v1-5 with segmentaion.
Access
Public
Updated Apr 10, 2024
Repo size
7.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth1.4 GB · 100%
At a glance
- Task
- Image-to-Image
- License
- mit
- Access
- Public
- Created
- Mar 27, 2024
- Updated
- Apr 10, 2024
- SHA
- 591d167b
Model card
From the Hugging Face model README
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.
Training Method
- Train on ControlNet-ade20k for 30 epochs.
- Train on SAM-COYO-3k for 30 epochs.
- Train on COCO2017 for 1 epoch.
- Task
- Image-to-Image
- License
- mit
- Languages
- en
- Created
- Mar 27, 2024
- Updated
- Apr 10, 2024