omniAI supports a number of AI Image models. 


Dalle3 by OpenAI

DALL-E 3 is a text-to-image model developed by OpenAI. It takes a text prompt and generates an image based on that prompt. DALL-E 3 is a fast and easy-to-use tool that produces high-quality images. DALL-E 3 is a significant advancement in the field of text-to-image generation, and its ability to create realistic images from text descriptions has the potential to revolutionize how we create and share visual content.


Imagegen3 by Google

Imagegen3 by Google is a text-to-image model that generates images based on a prompt. It is fast, produces high-quality images, and can handle complex prompts. Learn more at https://deepmind.google/technologies/imagen-3/


Imagegen3 Fast - Google

Imagegen3 Fast by Google is a FAST text-to-image model that generates images based on a prompt. It is fast, produces high-quality images, and can handle complex prompts.


Stable Diffusion 3.5


  • Stable Diffusion 3.5 Large: At 8.1 billion parameters, with superior quality and prompt adherence, this base model is the most powerful in the Stable Diffusion family. This model is ideal for professional use cases at 1 megapixel resolution.

  • Stable Diffusion 3.5 Large Turbo: A distilled version of Stable Diffusion 3.5 Large generates high-quality images with exceptional prompt adherence in just 4 steps, making it considerably faster than Stable Diffusion 3.5 Large.

  • Stable Diffusion 3.5 Medium: At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution. 

Supported use cases
Media and Entertainment, Marketing and Advertising, Gaming, Retail, Consumer Products
Model attributes
Technology (encoders): OpenAI Clip L1/4, OpenCLIP bigG/14, T5-v1.1-XXL
Parameters: 2-8 Billion
Training Data: Extensive
Prompt following: Highly accurate captions in training
Text prompt: Enhanced text-to-image prompts
Typography: Versatility and readability across different sizes and applications
Noise predictor/conditioning: Multiple Diffusion Transformers
Composition: Improved scene layout, including object placement
Visual aesthetics: Realistic with finer attention to detail, model performs well with Anime, Cartoons and for Ideation

Stable Image Core

Create and iterate images quickly and affordably with Stable Image Core, the image service that requires no prompt engineering to get high quality images in diverse styles at high speed.

Supported use cases
Media and Entertainment, Marketing and Advertising, Gaming, Retail, Consumer Products
Model attributes
Technology (encoders): OpenAI Clip L1/4, OpenCLIP bigG/14, T5-v1.1-XXL
Parameters: 2 Billion
Training Data: Extensive
Prompt following: Highly accurate captions in training
Text prompt: Enhanced text-to-image prompts
Typography: Versatility and readability across different sizes and applications
Noise predictor/conditioning: Multiple Diffusion Transformers
Composition: Improved scene layout, including object placement
Visual aesthetics: Realistic with finer attention to detail, model performs well with Anime, Cartoons and for Ideation

Stable Image Ultra 

Take your visuals to a whole new level with large, photo realistic output. Enable your organization to go from idea to execution faster, extend your existing resources to achieve more, and empower creative thinking at speed and scale by building on Ultra.


Supported use cases
Media and Entertainment, Marketing and Advertising, Gaming, Retail, Consumer Products
Model attributes
Technology (encoders): OpenAI Clip L1/4, OpenCLIP bigG/14, T5-v1.1-XXL
Parameters: 2 Billion
Training Data: Extensive
Prompt following: Highly accurate captions in training
Text prompt: Enhanced text-to-image prompts
Typography: Versatility and readability across different sizes and applications
Noise predictor/conditioning: Multiple Diffusion Transformers
Composition: Improved scene layout, including object placement
Visual aesthetics: Realistic with finer attention to detail, model performs well with Anime, Cartoons and for Ideation