Generate Images on Website

Creation Interface Instructions

Inference UI

01 Model Selection

Before generating images, you need to choose the appropriate model based on the desired content. PICPIK provides 8 pre-installed models by default, which can cover most image generation scenarios. If you have special requirements, you can train your own models using the training module, and these models will appear under the "Custom Models" category.

Pro Tip
Landscape models can not only generate realistic landscapes, but also be used for generating sci-fi style images.

02 Prompts

Prompts are the core module used for generating images. In traditional painting, brushes are used to create desired images, and prompts are like brushes in the field of AI image generation. You need to describe the content of an image by text.

How to Express the Image Content

There are two main ways to express the image content: complete sentences and keywords. You can use complete sentences to describe the image content, just like everyday conversation. When the image is more complex or you don't have a specific idea yet, you can use keywords separated by commas to describe the image. In fact, using keywords is more popular because it is easier to adjust and control.

Here are two examples of landscape images using different methods. You can try them yourself.

Complete Sentence:

The afterglow of the setting sun rises in the distant sky. The vast sea is calm and windless. Hundreds of wind turbines stand in rows on the mountains. The sky gradually darkens, and countless evening clouds gradually fade from brilliant to dim, like fireworks. Then, the night calmly descends on the bay, and lights start to illuminate the harbor one after another.


Setting sun, calm sea, wind turbines on the mountains, hundreds, evening clouds, bay, harbor, architectural lights, night

Negative Prompts

In general, we only need to enter the description in the positive input box. However, in some cases, to control the image, we want to avoid certain specific content. In this case, you can use the negative input box. The AI will try to avoid the content described by the negative prompts from appearing in the image.

Multilingual Switch

Currently, the majority of AI painting models are trained based on English prompts, so normally other languages cannot be used as prompts. When the multilingual switch is turned on, PICPIK will intelligently process and analyze your input via AI and vector database technology, supporting mixed input of Chinese and various other languages.

Dictionary and Auto-Completion

Click on the document icon in the upper right corner of the prompts input box to open the prompts dictionary. If you can't find a suitable expression, you can try using the vocabulary in the dictionary to assist in expressing the image content or improve the quality of the image.

In addition to manually opening the dictionary, when entering prompts, the keywords in the dictionary will also appear as auto-completion suggestions below the input cursor.

Advanced Grammar

You can use specific grammar to emphasize, weaken, or even mix prompts. The following are examples of related grammar:


The colons, parentheses, and brackets in the examples are all half-width English symbols. When using Chinese input after enabling multilingual mode, the system will automatically convert them to corresponding full-width Chinese symbols.

one (pen)The concept of a pen is strengthened by 1.1 times.
one ((pen))The concept of a pen is strengthened by 1.21 times. Each additional pair of parentheses increases it by 1.1 times.
one [pen]The concept of a pen is weakened by 1/1.1.
one [[pen]]The concept of a pen is weakened by 1/1.21. Each additional pair of brackets decreases it by 1.1 times.
one (pen:2)The concept of a pen is strengthened by 2 times.
one (pen:0.5)The concept of a pen is weakened by 50%.
one [pen:arrow:0.5]The first 50% of the steps generate a pen, and the last 50% of the steps generate an arrow. The final result is a mixture of an arrow and a pen.

03 Reference Image

If you need to generate an image similar to an existing image, you can upload the existing image as a reference. The reference intensity in the reference image module refers to the weight of using the reference image. If the reference intensity is 100%, the generated image will be identical to the original image.

When using a reference image, you can either leave the prompt words blank or add some additional prompt words. The additional prompt words will be used together with the reference image as guidance for generating the image.

04 Size

Refers to the size of the generated image. Free accounts support images with a maximum width / height of 512 pixels, while paid accounts support images with a maximum width / height of 1440 pixels. If the image size does not meet your requirements, you can use a refinement function to enlarge it.

05 Quantity

Refers to the number of images generated at one time. Up to 16 images can be generated at once. Please note that if you are a free user, only the last 8 images will be kept in your history.

06 Advanced Generation Parameters

Refers to the advanced parameters used during image generation. We have already configured the optimal parameter settings for the pre-installed models. If you are not familiar with the relevant concepts, it is recommended to use the official settings without making any changes.

07 Image Generation

Click the generate button to generate images based on the above settings. The remaining inference count, which represents the maximum number of images that can be generated, is displayed to the left of the generate button.

08 Preview and Refinement

The most recently generated images will be automatically displayed in the preview area. Below the image preview area are the related operations for the image:

Preview Toolbar

Download and Share (A)

Click the download button to download the original image.

Reuse Generation Parameters (B)

Reuse the generation parameters of the current image to generate a new one. The "Use Prompt Words" button is to reuse the prompt words of the current image. The "Use Seed" button is to reuse the Seed of a existing image. The Seed is commonly used to ensure consistent content in the generated image. If you are not familiar with the relevant concepts, you can ignore it. The "Use All Settings" button, as the name suggests, will reuse all the parameters and settings.

  • Since most models are trained based on English, when using multiple languages, the system will automatically process the prompt words into English. Therefore, when reusing prompt words, you will see the processed English prompt words in the prompt word input box.
  • Images generated using reference images or images generated using refinement functions may not support the reuse otpions.

Refinement (C)

The refinement functions of a image are concentrated in this module.

HD Enlargement

Enlarge the current image using AI algorithms. If it is an image in the style of anime, it is recommended to use the algorithm specifically designed for this style.

Face Swap

Use uploaded images to replace faces in the current image using AI algorithms. You can specify the target face to be replaced by a number. The default value of 0 represents the first face appearing from left to right and top to bottom. 1 represents the second face, and so on.

PS Plugin Download

Photoshop Plugin
The PS plugin supports editing and modifying the image content directly on the canvas through selection, providing more comprehensive image control and refinement functions, which are more suitable for professional users' workflow. If you are a Photoshop user, it is strongly recommended to dowload the plugin.

Delete Image (D)

Permanently delete the current image, and it will not appear in the history of images.

09 Interface Language and Personal Information

Switch the interface language by clicking the language switch button. Use the dropdown menu under personal information to view and modify your account information.

10 Historical Images

Displays the historical images you have generated. Free users can keep the most recent 8 images, while paid users can keep the most recent 256 images. Click on an image to preview it in the image preview area. Right-click on a historical image to display the related operations for that image.