【SD Tutorials】Png Info and Other features You Need to Know

Noodle

March 10th, 2023

Contents

PNG Info
Checkpoint merger
Train
Settings

PNG Info

Write the generated parameters to the image png file so that the image will quickly get Prompt. If the image is generated by Stable Diffusion, you can use the Send to buttons to quickly copy the parameters to various pages.

Checkpoint merger

Checkpoint merger is for combining two or more models. You can combine up to 3 models to create a new model. Primary model (A, B, C): The input models. The merging will be done according to the formula displayed. The formula will change according to the interpolation method selected. Interpolation methods:No interpolation: Use model A only. This is for file conversion or replacing the VAE. Weighted sum: Merge two models A and B, with multiplier weight M applying to B. The formula is A * (1 – M) + B * M. Add difference: Merge three models using the formula A + (B – C) * M.

-ckpt: The original checkpoint model format. -safetensors: SafeTensors is a new model format developed by Hugging Face. It is safe because, unlike ckpt models, loading a Safe Tensor model won’t execute any malicious codes even if they are in the model. -Bake in VAE: Replace the VAE decoder with the one selected. It is for replacing the original one with a better one released by Stability.

Train

The Train page is for training models.The training model will be explained later in the tutorial.Click here you can know more.

Settings

Make sure to click Apply settings after changing any settings.

Face Restoration

Make sure to select the default face restoration method.

Stable Diffusion

Download and select a VAE released by Stability to improve eyes and faces in v1 models.VAE：VAE stands for variational autoencoder. It is the part of the neural network model that encodes and decodes the images to and from the smaller latent space, so that computation can be faster.More details will come later in the tutorial.

About How to Use Text2img click here , and How to Use Image2img click here. Stable Diffusion Tutorial Guide click here.