Learned from Stable Diffusion, the software is offline, open source, and free.
In the realm of image generation, a new star has emerged on the horizon—Fooocus. This groundbreaking software stands as a culmination of inspiration drawn from two pioneering predecessors, Stable Diffusion and Midjourney, yet it propels the concept of image generation into an entirely new dimension. At its core, Fooocus embraces the philosophy of combining the best of both worlds while discarding the complexities that often deter users from exploring the vast landscapes of digital creativity.
Incorporating the essence of Stable Diffusion, Fooocus proudly upholds the values of accessibility and freedom. Operating offline, and offered as an open-source solution, this software empowers users to dive into the realm of image generation without constraints. Beyond the barriers of cost or connectivity, Fooocus provides a canvas where imagination knows no bounds.
Below is a test on a relatively low-end laptop with 16GB System RAM and 6GB VRAM (Nvidia 3060 laptop). The speed on this machine is about 1.35 seconds per iteration. Pretty impressive – nowadays laptops with 3060 are usually at very acceptable price.
Note that the minimal requirement is 4GB Nvidia GPU memory (4GB VRAM) and 8GB system memory (8GB RAM). This requires using Microsoft’s Virtual Swap technique, which is automatically enabled by your Windows installation in most cases, so you often do not need to do anything about it. However, if you are not sure, or if you manually turned it off (would anyone really do that?), you can enable it here:
Image instruction below