New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Questions about Appearance Regularization Dataset #3

Open

yoshioka2443 opened this issue Jul 23, 2024 · 1 comment

yoshioka2443 commented Jul 23, 2024

I have two questions regarding the dataset used for Appearance Regularization (specified with --reg_data during training).

How did you create the dataset? Could you please provide details about the specific model used for image generation and the commands executed? Additionally, I would appreciate it if you could share the list of prompts inputted into image2text.
How many images are required?
Thank you for your assistance.

Owner

Mq-Zhang1 commented Sep 16, 2024

Stable diffusion 1.4 is used to generate the images, other model versions also work. You may refer to this page for code and command https://huggingface.co/CompVis/stable-diffusion-v1-4. Below are some prompt examples that may help.
scene_prompt.txt
I generated around 40k scenery images in total for training

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment