SDXL Models

Stability AI offers a range of open-source AI models for image generation, including the SDXL model. These models are highly versatile and can be further developed by the community of developers, leading to various model variations available on platforms like CivitiAI.

One of the key advantages of the Stability AI models is the ability to generate images of any size without restrictions. At Qolaba AI, we have handpicked some of the best community-trained models and made them available on our platform. These models include SDXL, Qolaba, Realistic, Anime, Cartoon, and Qolaba Turbo.

Selecting the Model

To get started, navigate to the "Model" section and choose the model that best suits your needs. Here's a brief overview of the available models:

  • SDXL: The base variant of the SDXL model, provided by Stability AI.

  • Qolaba: A ProtovisionXL model fetched from the CivitiAI platform, with impressive capabilities in generating content across various categories, such as 3D, photorealism, anime, and hyperrealism.

  • Realistic: A NewRealityXL model from the CivitiAI platform, known for its ability to generate high-quality realistic content.

  • Anime: A DeepBlueXL model from the CivitiAI platform, specializing in creating stunning anime-style images.

  • Cartoon: A DynaVisionXL model from the CivitiAI platform, capable of generating amazing 3D and traditional cartoon content.

Entering the Prompt

After selecting the model, you can enter your desired prompt or text description in the "Prompt" text box. For more information on crafting effective prompts, including the use of magic prompts, style presets, negative prompts, and keywords, please refer to the Prompt Advancement.

Selecting Image Settings

On the right-hand panel, you can choose the number of images you want to generate based on your prompt. Below this, you'll find options to select the desired aspect ratio, such as ultrawide, portrait, or square. For more details on resolution, please refer to the Resolution.

Additionally, you can choose the prompt guidance and quality settings. More information on these options can be found in the Generation Settings Guide.

Generating the Images

Once you've entered your prompt and selected the desired settings, click the "Generate" button on the left-hand panel. You can choose from three inference types: Normal, Fast, and Hyper. The Normal option is cost-efficient and fast, while the Fast and Hyper options can generate images more quickly but at a higher cost. For more details, please refer to the Generation Settings Guide.

Once you click on "Generate" button, model will generate the image based on given configuration.

Resetting the Process

If you wish to start over, you can find a "Reset" option at the bottom of the right-hand panel.

Image Editing

After generating the images, you can click the hamburger menu to access the image editing options. For more information on the available editing tools, please refer to the Image Editing Options Guide.

Private Content

The left-hand panel also includes an option for "Private Content." For details on this feature, please have a look at Private Session Guide.

Last updated