SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Diffusion-based text-to-image models have made great strides at synthesizing photorealistic content from text prompts, with implications for many different areas of study, including but not limited to: content creation; image editing and in-painting; super-resolution; video synthesis; and 3D assets production. However, these models need a lot of computing power, hence

computing computing power devices diffusion diffusion model editing image image diffusion mobile mobile devices painting photorealistic power production prompts stable diffusion study synthesis text text-to-image theory video