Adding Conditional Control to Text-to-Image Diffusion Models
Paper
•
2302.05543
•
Published
•
58
This checkpoint is a finetuned version based on the the lllyasviel depth checkpoint. It can be used in combination with Stable Diffusion, such as stable-diffusion-v1-5/stable-diffusion-v1-5.
The finetuning was done using an adapted version of diffusers. For more details have a look at the 🧨 Diffusers docs.
This checkpoint corresponds to the ControlNet conditioned on Google Earth rendered depth images.
For more information, please also have a look at the Diffusers ControlNet Blog Post and have a look at the official docs.
Base model
runwayml/stable-diffusion-v1-5