Skip to content
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.

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

Questions about Custom Diffusion with artistic styles #48

Closed
BossunWang opened this issue Mar 10, 2023 · 1 comment
Closed

Questions about Custom Diffusion with artistic styles #48

BossunWang opened this issue Mar 10, 2023 · 1 comment

Comments

@BossunWang
Copy link

Hi, expert
I'm interest on Figure.9. which generated style of artist.
May you share how to train the V1* art and more detail to combine with V2* wooden pot?

@nupurkmr9
Copy link
Collaborator

Hi, if you are using the CompVis based training code, you can train for a particular style using the following command.

wget https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt 
bash scripts/finetune_style.sh "art" <path-to-style-images> real_reg/samples_art <name-of-the-exp>  finetune_addtoken.yaml  sd-v1-4.ckpt 

This is the command to train a joint model with given style with the "wooden pot".

bash scripts/finetune_joint.sh  "art" <path-to-style-images> real_reg/samples_art  "wooden pot" data/wooden_pot real_reg/samples_wooden_pot  <name-of-the-exp> finetune_style_joint.yaml sd-v1-4.ckpt 

Hope this is helpful. Let me know if you are interested in the diffusers based script for the same or have any other doubts.
Thanks!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants