Get a weekly rundown of the latest AI models and research... subscribe!

Pixart Xl 2


AI model preview image
PixArt-Alpha 1024px is a transformer-based text-to-image diffusion model that takes specific text prompts and transforms them into detailed, high-resolution artistic images with a size of 1024x1024 pixels. The model is trained on text embeddings from T5 and it can be customized by adjusting various parameters such as style, guidance scale, number of outputs, scheduler, and number of inference steps. The output of the model is a URL link to the generated image.

Use cases

PixArt-Alpha 1024px is a text-to-image diffusion system based on transformer AI technology, offering potential use in a variety of digital and visual media applications. As it utilizes text inputs to generate high-resolution images, this AI model, pixart-xl-2, could potentially serve a wide array of practical uses. This could range from graphic design, advertising, animation, and content creation for social media, to more niche applications like architectural visualizations or game development, where designers need to quickly generate conceptual visuals. It could also have utility in education, helping teachers to create custom visual aids, or even in film and television, generating scene layouts or storyboards based on script excerpts. For example, the text prompt "an astronaut sitting in a diner, eating fries, cinematic, analog film" could render a visual interpretation of that scenario for use in pre-production of a film or a digital art piece. The possibilities for pixart-xl-2 are numerous, as it blends creative and technical fields, opening the door for new approaches to generating digital imagery based on text prompts.


Cost per run
Avg run time

Creator Models

Realvisxl2 Lora Inference$?1,987
Wizardcoder 15b V1$?459
Vicuna 13b V1.3$?3,554
Wizardcoder Python 34b V1.0$?830

Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the Pixart Xl 2 model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NamePixart Xl 2

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system t...

Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-