Text to Image Models Leaderboard

Text to Image Models
Leaderboard

Text-to-Image models have significantly revolutionized the conventional notion of creativity, serving as a transformative force in the realm of generating visual content from textual input.
Problem: The availability of numerous Text-to-Image models in the market poses challenges in evaluating their effectiveness as the relevant information based on it is scattered across the internet.

Solution: We have developed a leaderboard specifically designed for researchers seeking to identify top-performing text-to-image models. Utilizing an intuitive leadership quadrant graph, we evaluate the code models' performance, capabilities, and market adoption to provide comprehensive rankings.View Models

Leaders

As of June 20, the current leaders in text-to-image models are Stable Diffusion 2, Stable Diffusion 1, and DeepFloyd, with respective scores of 80.935, 69.5, and 68.19 based on our scoring methodology. Stable Diffusion 2, released in November 2022, is the current frontrunner and evolution of the original Stable Diffusion model. Trained on an extensive dataset of 1.5 trillion images and text descriptions, it generates highly realistic and intricate images. This model incorporates a novel text encoder derived from the OpenCLIP model, enabling a deeper understanding of text prompts and yielding improved image generation outcomes. Furthermore, Stable Diffusion 2 offers enhanced stability and efficiency compared to its predecessor. Stable Diffusion 2 can generate images with resolutions of up to 768x768 pixels, which is much higher than the resolution of images generated by traditional GAN models.

Rank	Model	Size	Architecture	Organization	Adoption Rating Calculated based on the number of forks and stars on the official model repo.	Capability Rating Calculated based on the number of tasks and downstream tasks of the model.	Score A weighted average of the adoption and capability score of the model.
#1	Stable Diffusion 2	1.5T	Diffusion	Stability AI	82	79.87	80.935
#2	Stable Diffusion 1	500B	Diffusion	Stability AI	90	49	69.5
#3	IF	1B	Diffusion	DeepFloyd	43	93.38	68.19
#4	Kandinsky	1B	Diffusion	University of Chicago	33	82.53	57.765
#5	Karlo	1.56TB	unCLIP	University of Oxford	6.8	41.3	24.05

Need help with Generative AI?

If you have any questions or need a helping hand, don't hesitate to reach out.

Let’s Get Started

The first step towards greatness begins now, let's embark on this journey.

Help us Help you.

Share more information with us, and we'll send relevant information that cater to your unique needs.

Final Touch

Kindly share some details about your company to help us identify the best-suited person to contact you.

Contact Details

First Name*

Last Name

Email*

Country Code

Phone Number

Methodology

We only considered prominent and text-to-image models to create this leaderboard. Note that this leaderboard can only be considered a high-level indicator of overall performance. Depending on the specific use case and business requirements, a low-performing model in this leaderboard may be more favorable than a high-performer. The key parameters used for the scoring are;

Benchmark results
Model forks
Model stars

Capability Rating(CR) is calculated based on the average of the selected benchmark results(BR) published in the Model's research paper.

CR = Σ(BR)/COUNT(BR)

Adoption Rating (AR) is calculated based on Model forks (MF) and Model Stars (MS). Model Stars directly indicate the community's acceptance of the Model. However, the number of stars does not necessarily mean the Model is used for project implementations. Model forks can indicate community adoption of the Model for building different applications. To calculate the adoption rating, we calculate the ratio of MS vs. MF and normalize the value to 100.

AR = NORM(MS/MF)

The Model score is simply the average of scores Adoption Rating and Capability Rating.

White Papers

Products

MENU

Text to Image Models Leaderboard