StableDiffusionWebUI: Image Info (PNG Info)

Preface

PNG Info is a built-in feature of sdwebui

that is essential in everyday image generation workflows.

PNG Info

Simply put, you upload an image,

it reads the image’s meta information,

parses the generation parameters,

and allows you to conveniently send them to other features

such as txt2img, img2img, inpainting, etc.

Usage is straightforward — under the PNG Info tab,

upload an image and it will automatically parse the information.

This is perfect when you come across an interesting image

but don’t know which checkpoint, LoRA, embeddings, or prompts were used.

It is an essential feature for beginners learning AIGC image generation.

The parsed information is divided into several parts.

Positive Prompt

Note that LoRA references are usually included here. In that case, you need to download the corresponding LoRA and ensure the naming is consistent.

For example, this image uses the naruto LoRA.

For LoRA usage, see: https://blog.vincentqiao.com/sd-lora

Negative Prompt

Negative prompts usually contain embeddings.

You also need to download the corresponding embeddings and ensure the naming is consistent.

For example, this image uses embeddings such as badhands, easynegative, etc.

For embeddings usage, see: https://blog.vincentqiao.com/sd-embeddings

Model

This refers to the checkpoint, which is crucial.

Using the same checkpoint produces images with a similar style.

For example, this image uses the counterfeit checkpoint.

For checkpoint usage, see: https://blog.vincentqiao.com/sd-checkpoint

Other Information

The remaining information includes common generation parameters such as:

Steps, see: https://blog.vincentqiao.com/sd-steps

Sampler, see: https://blog.vincentqiao.com/sd-sampler

Hires.fix, see: https://blog.vincentqiao.com/sd-hiresfix-m https://blog.vincentqiao.com/sd-hiresfix-d

Summary

PNG Info is an essential feature.

By following the information parsed by PNG Info, you can easily replicate any image you find interesting.

SDWebUI

|—Link: https://sdwebui.ai/?from=vq

|—Authentic Stable Diffusion WebUI V1.10.1~

|—Top-tier 4090 GPU, premium members get exclusive single 4090 card for image generation~

|—Supports Mac client, Windows client, and Web online usage~

|—Innovative instant model transfer feature, instantly use local models~

|—Supports txt2img, img2img, extras, and PNG info

|—Supports CLIP interrogation and DeepBooru interrogation

|—Supports Hires.fix with 21 built-in upscaling models

|—Supports ADetailer with 11 built-in repair models

|—Supports ControlNet with 44 built-in preprocessors and 68 built-in models

|—Supports super-resolution upscaling (Tiled Diffusion, Demo Fusion, Tiled VAE)

|—Supports old photo restoration with 21 built-in upscaling models, plus GFPGAN and CodeFormer restoration models

|—Built-in 2 common Styles, 11 popular Checkpoint models, 7 popular LoRA models, 14 common embeddings

|—Built-in oldsix prompt plugin

|—Built-in 23-lesson beginner tutorial