Hi there,
If you've tried out AI-powered image generators you'll have a fair idea of what they are capable of. Well, there is a new one on the market from Stability AI called Stable Diffusion This text-to-image generator has been developed in collaboration with HuggingFace and CoreWeave.
Stable Diffusion is released under a Creative ML OpenRAIL-M license, which permits both commercial and non-commercial usage. It also incorporates an AI-based Safety Classifier, ensuring the generation of desired outputs while adhering to ethical and legal norms.
While the model holds immense potential, it is still under refinement. Stability AI encourages community feedback to further improve this technology. They have also created a dedicated community for Stable Diffusion for ongoing discourse and development.
Stable Diffusion competes with popular AI-powered text-to-image generators such as Midjourney, Dall-E 2, and more. Here's a quick example of what Stable Diffusion can do.
Source
Currently, Stable Diffusion will need about 6.9GB of VRAM for processing images quickly and works best with NVIDIA chips. However, Stability AI is working on enhancing it for AMD, and Apple M1/M2 chipsets.
If this looks impressive, you should check out our list of the top AI-powered image generators.
Stay tuned for more updates on this transformative technology!
Cheers!
Aditya
Are You Reading This In Gmail?
Update Your Email Preferences.
0 Komentar untuk "AI Weekly: There's a New AI-Powered Image Generation Tool in Town"