# Maze Guru Web

Where can I find it?

You can access it by logging in with your Discord credentials at: [https://maze.guru](https://maze.guru/)

## What can I do on the web platform?

**Square:**Choose the character you need to have a conversation with

**Profile:** View all the images you have generated and access your personal information. 

**Gallery:** Browse through the public images available in the gallery. 

**Challenge:** Participate in activities and earn rewards. 

**Support:** Access FAQs and get additional help. 

**Pricing:** Subscribe, purchase, or earn points to continue creating images.

**Enterprise:**You can now use the API to add all the features of Maze Guru to your product

## Login with your Discord account

Click on the 'Sign up' button located in the upper right corner.

<figure><img src="/files/wDS1axNRAcLuPcROYFMW" alt=""><figcaption></figcaption></figure>

This will redirect you to the Discord verification page.

<figure><img src="/files/wQk5vNDY0DDo9lTEVEww" alt=""><figcaption></figcaption></figure>

Press the 'Authorise' button to complete the verification process.

<figure><img src="/files/iDrJYSwdxNqejujDuI89" alt=""><figcaption></figcaption></figure>

Once authorized, you will be able to check your profile and view the images.

## View your account information

go to the account page, view your current plan, current available pointa and rewarded.

view your points history,news center and order detail

## Accounts settings

Connect multiple accounts to your user and sign in with any of them.discord ,google and phone number

you can set private mode,In this mode, all your drawings will become visible only to you.

You can use an API key to interact with the site through the API as your user. These should not be shared with anyone.

## Create an image by text（Chat mode）

Visit character square, select a character to start your conversation

each character has different image style

<figure><img src="/files/t6CbJvYd9ei0ii3XHs2P" alt=""><figcaption></figcaption></figure>

* Enter your desired text prompt.
* Select the style, art genres (optional), and size.
* choose the number of drawings
* type the seed value(default -1)
* add negative prompt (option)
* send the message and waiting response

<figure><img src="/files/xIpwsJ1TAA2QNJVog6zl" alt=""><figcaption></figcaption></figure>

you can see all your artwork in "File Storage" page

<figure><img src="/files/URn3IafZXEY3gUHGq0cT" alt=""><figcaption></figcaption></figure>

## Create an animation by picture

Choose animation character in character square page

<figure><img src="/files/ZbIwN9gTnups4LH5vvzH" alt=""><figcaption></figcaption></figure>

Upload a file or choose the file you create in Maze

<figure><img src="/files/kHvIg77SS22n0RCKd2b7" alt=""><figcaption></figcaption></figure>

Send the picture and waiting. it will response the video for you

## Create an image by text (Classic mode)

Visit the Maze Guru website and navigate to the create page.

<figure><img src="/files/mmnyltoMkCaYMO2Y8QpL" alt=""><figcaption></figcaption></figure>

* Enter your desired text prompt.
* Select the style, art genres (optional), and size.
* type the seed value(default -1)
* Click the 'Create Now' button.

<figure><img src="/files/I3pe8PxkUG4cQtLDqyXG" alt=""><figcaption></figcaption></figure>

Your image will appear in the right panel.

<figure><img src="/files/RHw4O1mkMKnQvVHUJKrw" alt=""><figcaption></figcaption></figure>

## Create an image by image (Classic mode)

Go to the create page on the Maze Guru website and upload the seed image.

<figure><img src="/files/rlf84oK8j6krp7yUQP1F" alt=""><figcaption></figcaption></figure>

Click the 'Create Now' button. Your image will be displayed in the right panel.

<figure><img src="/files/7ORHfkE1s57jNGHPG4od" alt=""><figcaption></figcaption></figure>

## Gallery

Explore the gallery to view beautiful images created by other users.

<figure><img src="/files/VYoRu8qBrHtk7It8LGwl" alt=""><figcaption></figcaption></figure>

Click on an image to access the detail page and view the associated prompt.

<figure><img src="/files/SpWTRqbq2r82Fs2Hua0j" alt=""><figcaption></figcaption></figure>

## ControlNet

<figure><img src="/files/pvJESVE4gqW81bdLa21l" alt=""><figcaption></figcaption></figure>

1、Openpose

Openpose can use your uploaded character picture as a reference picture for AI painting, extract the pose and movement of the character, and generate a picture of the same pose, the effect is accurate and amazing.

2、Depth

Depth can infer the depth of the input image based on the character map, building map or scene map you upload, and then use the text and depth information to generate a new image and retain more structural and hierarchical details.

3、Scribble

Scribble can color a picture or line draft uploaded by users to generate a gorgeous graffiti picture. Suitable for coloring characters.

4、Canny

Canny uses the pictures uploaded by users as reference pictures, extracts the line drafts, and then uses AI to accurately draw the line drafts. It can retain and restore more picture details.

5、Normal

Normal generates a modeling-style preprocessing image based on the image uploaded by the user, and then generates the image. It is suitable for character modeling and architectural modeling, and the effect of character modeling is better.

6、Seg&#x20;

Seg can cooperate with the picture description to carry out semantic analysis on the picture uploaded by the user, identify the information contained in the picture, segment the content of the picture, and show the segmented area.

7、Mlsd

Mlsd will recognize the lines and contours of the architectural diagrams, object diagrams and scene diagrams uploaded by users, generate preprocessed diagrams, and then generate pictures.

## Seed Image

Use seed image to create a picture from a picture. Creativity is the soul of the picture. The creativity setting varies greatly according to specific needs, so the absolute value has little reference significance. You should look at the relative value. If it is too much, it will be reduced, if it is not enough, it will be increased. 0 means completely the original image, 100 means completely new image. In experience, 50 is used as a distinction: before 50, most of the original content can be maintained, and otherwise, more will be created.

## Prompt Generator

<figure><img src="/files/wXnYcjEXa4kUGw48R2Km" alt=""><figcaption></figcaption></figure>

Prompt Generator can help you quickly generate prompts that AI can understand. user can pick some words from list

## Random Inspiration

Random Inspiration can help you randomly generate prompts

## Describe

The technology of generating text from images belongs to the field of computer vision, which is the technology of identifying the objects in the image from the image, through the CLIP (Contrastive Language–Image Pre-training) model based on AI computing technology. The relationship between pictures and text descriptions is greatly shortened. Simply put, the training method of the CLIP model is to associate pictures and text. Therefore, using the CLIP model can provide text descriptions for pictures.

## random seed

&#x20;An independent and unique number for each generated graph, -1 represents random generation. Under the same number, word parameters and model settings, the images generated each time are independent and unique. This means that the painting results can be restored by regenerating with the same combination.

## Upscale

Enlarge the image to a clearer size


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.maze.guru/maze-guru/maze-guru-web.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.