PixArt Sigma Image Generation

Generate high-fidelity 4K images from text prompts using PixArt-Sigma, a state-of-the-art diffusion model.

PixArt-Sigma achieves superior image quality and alignment with prompts compared to previous models like PixArt-alpha. It does so efficiently, evolving from PixArt-alpha through a process termed weak-to-strong training - leveraging higher quality data and an improved attention mechanism.

With just 0.6 billion parameters, PixArt-Sigma reaches new heights in text-to-image generation. Output stunning, intricate 4K images for posters, wallpapers, concept art, and more. Guide the model with descriptive prompts and fine-tune parameters like guidance scale and number of inference steps.

For more information, visit the original repository and follow the HF Space creator on Twitter at @artificialguybr.